2026-11-11 · GitHub AI Daily

Window2026-11-10 10:30 to 2026-11-11 10:30 (Beijing time), corresponding to GitHub default-branch commits with `committer-date >= 2026-11-10T02:30:00Z`. This issue collects **195** entries, including 5 picks, distributed as ① 62 / ② 32 / ③ 28 / ④ 73.

CoverageAI Coding / coding agents and the skill ecosystem · Medical / clinical-research AI and agent skill libraries · Health management / nutrition and food AI · Model foundation and agent infrastructure

De-duplicationChecked entry by entry against all 22 issues published from 10-16 to 11-10 (by extracting the full historical repository set — **1360** repos — with `grep -ho "https://github.com/[^/]*/[^/]*"` and comparing in lower case so that case variants do not slip through). All **195** entries in this issue are first-time appearances with zero repeats, and all 5 picks are first-time inclusions. This round collected **11762** unique `search/repositories` candidates (160 single-word queries with a `pushed:>2026-11-09` date filter, merged with the previous round's collection over the same window), plus **33** repositories scraped from the GitHub trending daily / weekly / monthly boards and verified individually. After removing history repeats, SEO spam and clearly off-topic entries, **9535** non-history candidates remained; each was then checked against the core endpoint `GET /repos/{o}/{r}/commits?since=&per_page=1` for real default-branch commits (multi-threaded, reading the `Link` header `rel="last"` page number as the exact commit count), **leaving 2828 repositories with genuine activity in the window** (of which 33 came from the trending boards — a trending listing is not itself proof of action today, so each was verified separately before inclusion). Manual selection and information-density screening produced the final 195. **Any repository whose `pushed_at` looked fresh but whose commits fell outside the window after per-repository verification was dropped; `pushed_at` alone is never the basis for inclusion.**

VerificationEvery "has activity today" entry is confirmed against GitHub commit records, and **exact commit counts always come from the `Link` header `rel="last"` page number on the core endpoint** (with `per_page=1` the page number is the total). **Stars and licenses are a live GitHub API snapshot** (as of 2026-11-11 10:30 Beijing time). **Licenses are read from the actual LICENSE file via `GET /repos/{o}/{r}/license`; the API `spdx_id` is only a lead** — this round, `ranxianglei/billion-context` and `heymrun/heym` report `NOASSERTION` while the real text is **MIT**; `Tencent/LoopForge` is a **Tencent custom open-source license statement**; `ralforion/orionbelt-semantic-layer` is **Business Source License 1.1** (source-available, not open source); `Arize-ai/phoenix` is **Elastic License 2.0**; `TrenTorch/TrenTorch` is **PolyForm Noncommercial 1.0.0** (research and non-commercial use only); `pinellolab/CRISPResso2` is a **limited academic non-commercial license**; `camlab-bioml/rakaia` is an **all-rights-reserved proprietary notice**; `GiovanniDelGaudio1994/forma-ai` and `AA-0324/meliusme` are **proprietary software licenses**; `Dicklesworthstone/coding_agent_session_search` is **MIT plus an OpenAI/Anthropic rider**; `tuist/tuist`, `SourceWeft/SourceWeft`, `HL7/fhir`, `crbnos/carbon`, `OneUptime/oneuptime` and `ExplosiveCoderflome/AI-Novel-Writing-Assistant` all use **multi-license or dual-track terms**. A further **18** entries were individually confirmed to have **no LICENSE file in the repository root** (including two of this issue's picks, `Prabh54/groundedmed` and `shubhampawar05/nutrikit`) and are marked "Unstated" in the tables — **"Unstated" does not mean "no terms apply", but it must be re-checked at selection time.** Of the 195 entries, MIT and Apache-2.0 together account for 128 (66%), and 146 (75%) are permissive once BSD / ISC / MPL / CC0 are added; 17 are copyleft (AGPL-3.0, GPL, LGPL) and readable but not copyable; 3 are source-visible but not open source (ELv2 / BUSL-1.1 / PolyForm NC); 6 use multi-license or custom composite terms; 4 are proprietary or academic non-commercial; and 18 have no LICENSE file at all. Selection should triage these into three tiers.

1. Today's picks (5)

1. Prabh54/groundedmed: A biomedical RAG agent that has to prove it did not make anything up

URL: https://github.com/Prabh54/groundedmed ｜ ★0 ｜ Unstated ｜ Research demo: agentic RAG that gives citation-checked answers to biomedical yes/no/maybe questions, refuses when evidence is weak, and publishes its results from a frozen 200-question PubMedQA test. Not medical advice.

What happened

v1.1.0 shipped at 2026-11-11 02:24, barely more than a day after the public v1.0.0, adding a critic-guided rewrite plus a second hash-locked test set; production smoke-test results were published on the README and the /eval page in the same run.
The pipeline is a four-stage agentic RAG: planner, retriever, answer writer and critic. Answers come back as yes / no / maybe, and every finding must point at the abstract it came from.
Citation checking is done by code, not by the model's own word: the program verifies each citation, and the critic re-checks every finding against the abstract it cites. When the critic flags an answer that should have been refused, the writer gets one guided rewrite and the critic checks it once more.
Evaluation runs on hash-locked PubMedQA splits: the decision rules for the second 400-question set were written down before the run, and both the baseline and agent scores are published side by side.

Why it matters

This is the ruler my public-account content is missing. On 11-09 I wrote down a to-do for myself: every extraction must carry the source location, and if it cannot, it must not enter the report. GroundedMed is stricter than my sketch — not just "cite the source" but machine verification first, then a critic model that does not know the answer checks each finding against the original text. It is the mirror image of the bpf-benchmark pattern I noted on 11-10: replace "I say I am right" with "an uninvolved third party decides."
"Not enough evidence" as product behaviour is copyable. I have always worried that my GRPM intervention reports will let the model fabricate a conclusion when the evidence is thin. GroundedMed writes not enough evidence into product behaviour — that is product design, not prompt tricks.
The hash-locked test set is worth copying wholesale. Freezing the decision rules for the second 400-question set before the run is the cure for the classic failure mode of my A/B tests: setting the standard after seeing the results. My next step is to freeze one version of the GRPM SNP-extraction rules the same way.

2. Muratovnik/assay: A gate that forces coding agents to list every file they actually read

URL: https://github.com/Muratovnik/assay ｜ ★1 ｜ MIT ｜ Evidence-grounded methods for coding agents: skills and agent profiles for Claude Code, Codex, Cursor and Gemini CLI

What happened

v0.44.0 and v0.44.1 shipped within a single day on 2026-11-10, with v0.44.1 targeting the visibility of skill file checkouts.
The core is a set of hooks that binds a read claim to the file it names. The commit messages are explicit: keep a read claim's file list going past a name with no Read; tie a read claim to every file its sentence lists; compare a full-read claim with the file its own clause names.
The other half is conditional skill loading: the existing-solutions section is requested from a plan only when the planning skill is loaded, and the skill-evaluation sign applies only to skills in a repository that is not a plugin.
Self-described as evidence-grounded methods for coding agents — skills and agent profiles, not a prompt library: executable evidence discipline bolted onto the agent.

Why it matters

This hits the biggest hole in my expert-package QC. My current approach is asking the model to grade itself — it claims it read a file and I believe it. Assay instead makes "I read this" carry a complete file list, with every listed name backed by an actual Read, and it goes red if one is missing. This is precisely the executable form of my 11-09 second to-do (every extraction must carry its source location): my version asks the model to write it down; this one makes the machine check it.
I am almost certain my own expert packages commit the failure mode "a read claim hanging off a name with no Read." A report says "based on this file's methodology" while the model only ever saw the filename — to a human reviewer the two look identical, but under an assay-style gate the difference surfaces instantly. This belongs on line one of my expert-package checklist.
"Only ask the question when the skill is loaded" holds for on-demand retrieval too. In my GRPM pipeline, SNP extraction rules should load only when a nutrition-relevant variant shows up; feeding them unconditionally doubles both token cost and hallucination surface.

3. vxxqv/openomicsbench: A locally runnable answer to "how do you validate omics software?"

URL: https://github.com/vxxqv/openomicsbench ｜ ★2 ｜ Apache-2.0 ｜ Offline RNA, DNA, protein, single-cell and genomic interval benchmarks with a five-assay demo and traceable reports.

What happened

v13.0.0 shipped at 2026-11-10 17:30, just two days after v12.0.0 — a tight release cadence.
The headline addition in v13 is RNA-seq input packs: packable per study or across all 12 biological objects, and each pack keeps the count matrix, the sample sheet and the declared contrast together, with checksums and a design preflight.
Result tables plug natively into DESeq2, edgeR and limma conventions and can be scored or converted directly; the repository also ships reference results, so it explicitly states that this is not a blinded challenge.
Offline operation is a hard promise: once installed it needs no network, sequence files stay on the local machine, and the bundled tools cover inspection and light preprocessing only — they do not claim to replace aligners, variant callers or taxonomic classifiers.

Why it matters

Checksums, a design preflight, and stating plainly how this differs from a blinded test — together these are exactly what my GRPM report lacks most. The 11-10 path I wrote down (archive data → fix decision rules → reproducible artifacts) is what openomicsbench has already packaged into something pip-installable, and the line "this is not a blinded challenge" is more candid than most papers.
It moves "is the method reproducible" from "I say so" down to "here is my published decision surface." Twelve biological objects, seven deterministic sequence and classification fixtures, a 10x-style single-cell benchmark and a peak-calling benchmark are reference materials you can read directly, not a leaderboard where everyone scores against different yardsticks.
The most practical use for me is as a counter-example library. In my GRPM pipeline the extraction and interpretation logic differs across each of the 40 nutrition-related SNPs; if the definition of "evidence strength for this recommendation" is redefined whenever the SNP batch changes, then cross-report comparison is theatre. openomicsbench is a standing reminder that decision rules should be version-frozen, not written afresh per report.

4. shubhampawar05/nutrikit: A self-hostable nutrition API with an MCP server — and it fixed a real-world food-matching gap

URL: https://github.com/shubhampawar05/nutrikit ｜ ★0 ｜ Unstated ｜ Self-hostable nutrition API: food search, portion-aware nutrients, meal logging from text, voice, photos, barcodes and labels, meal plans and an AI nutrition advisor. JS SDK on npm (@nutrikit/sdk).

What happened

Three commits in the window, the newest being #21 "fix/regional-food-matching", which also adds spelling correction — misspelled food names now produce respelling suggestions.
The concrete fix: matching dal makhani to CoFID's black gram and kidney bean curry — a genuine cross-database naming gap rather than a staged demo.
The shape is a complete self-hostable stack: nutrition API, website, developer portal, JavaScript SDK and an MCP server, with @nutrikit/sdk on npm and a free-API-key instance on Render.
The data surface covers 13,000+ foods with up to 33 nutrients each and understands portion expressions like "2 medium" or "1.5 cups"; there are text, voice and photo logging paths plus barcode scanning.

Why it matters

This is the only repository in this issue's health line about database semantics rather than photo-based calorie counting — and the latter accounts for the bulk of GitHub's health line. Photo food-recognition projects are everywhere; aligning a food name to a nutrient-database identifier is a problem only someone actually using the thing in production would hit, and the dal makhani case shows the author has hit that wall.
It ships an MCP server, which lines up directly with my GLP-1 nutrition companion and the 4P platform's integration needs. My nutrition data sources are currently scattered; consolidating onto one self-hostable, programmatically callable, versioned source is the direction I want — and self-hosting means a patient's diet data never has to leave the machine.
The respelling feature looks minor but is the first line of defence at the data entry point. When a user types a food name with a typo and the system silently fails to match and returns nothing, the user stops logging; offering a corrected candidate is what keeps logging rates intact. My nutrition companion's input layer should copy this interaction instead of returning an empty result.

5. chainloop-dev/chainloop: Turning "what the AI wrote" into an auditable trace

URL: https://github.com/chainloop-dev/chainloop ｜ ★611 ｜ Apache-2.0 ｜ Agentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs

What happened

Six commits in the window, with the main line being GitHub Copilot integration: #3801 "feat(trace): GitHub Copilot support (spec, plan, and M1)", #3804 "Copilot skills, spec pointers, and pasted images (M2)", and #3805 enabling Chainloop Trace hooks for Copilot.
Pi skill loads were folded into the record in the same period (#3759) — meaning which skill was loaded becomes an auditable event in its own right.
Self-described as agentic SDLC infrastructure: define guardrails, collect signals, enforce contracts.
Apache-2.0, with v1.134.0 released 2026-11-09 and v1.133.0 on 11-06, plus a fix making the lab compose stack work end to end (#3797).

Why it matters

"Which skill was loaded" becoming an auditable event matters more than the trace itself. My third to-do from 11-09 was to add "last verified time" and "does the target still exist" to every rule — but if I never recorded which rule set produced a conclusion, I cannot even begin to judge whether that conclusion has gone stale. chainloop records that step.
Running several hosts at once — Copilot, Claude Code, Pi, Codex — is now the norm, so logs from a single host are not enough. I run dsh, WorkBuddy and Ollama side by side locally, and any cross-host compliance requirement needs a host-agnostic recording layer — which is exactly where chainloop sits.
The most directly transferable idea for the 4P platform is the notion of a contract. If the input data snapshot, the decision-rule version and the citation list each carry a hash and are strung into one trace, report auditability stops being a wish and becomes one stage of a pipeline. That is the same road as the hash-bound evidence I noted under bpf-benchmark on 11-10, implemented differently.

2. Category roundup

① AI Coding / coding agents and the skill ecosystem

Project	Stars	One-liner
morluto/rea	★450,372	Reverse engineer anything with agents, from app behavior down to native binaries.
thedotmack/claude-mem	★115,891	Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
pbakaus/impeccable	★107,687	The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
heygen-com/hyperframes	★82,380	Write HTML. Render video. Built for agents.
pingdotgg/t3code	★55,913	(no description provided)
meta/astryx	★23,233	An open source design system that's fully customizable and agent ready
The-PR-Agent/pr-agent	★15,889	🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
langchain-ai/open-swe	★11,197	An Open-Source Asynchronous Coding Agent
nexu-io/html-anything	★9,495	✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex /
l0ng-ai/openidea	★8,427	The IDE you know, rebuilt in Rust. IntelliJ IDEA–style keymap, tool windows and search-everywhere in a fast native app: editor, code insight, debugger, Git, terminal, database and HTTP clients for 60+ languages.
logancyang/obsidian-copilot	★7,978	Run agents in Obsidian - OpenCode, Codex, Claude Code etc.
beenuar/AiSOC	★7,199	Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
ranxianglei/billion-context	★6,411	A context-compression plugin for month-long single sessions (billions of tokens), small context windows (a 100K context is enough) and token savings (5x fewer tokens).
tuist/tuist	★5,864	Tuist builds infrastructure for faster, more reliable build and test workflows across developers, CI, and coding agents. Shared cache, tests, and insights that sit alongside your existing CI.
callstack/agent-device	★5,327	Open source device layer for AI coding agents: a CLI, MCP server, and typed Node.js API to control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud.
michael-denyer/pstack-claude	★4,216	Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.
evalstate/fast-agent	★3,964	Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
yvgude/lean-ctx	★3,941	LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
Javis603/token-monitor	★3,629	Local-first desktop widget for tracking token usage, costs, limits, and session activity across 54+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.
taylorwilsdon/google_workspace_mcp	★3,501	Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool
ExplosiveCoderflome/AI-Novel-Writing-Assistant	★3,424	AI-native engine for end-to-end novel creation — from idea to full chapters, with structured planning, worldbuilding, and agent-driven workflows.
xiufengsun/TokenTracker	★2,224	Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness—with native apps. Never reads prompts.
nimbalyst/nimbalyst	★2,058	Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android
sweetpad-dev/sweetpad	★1,927	xcodebuild for humans and agents: build, run, debug, and test iOS, macOS, tvOS, watchOS, and visionOS apps from your terminal.
open-mercato/open-mercato	★1,919	The AI-Engineering Foundation Framework for business apps: open-source TypeScript, with multi-tenancy, RBAC, events and domain modules already decided as conventions and specs, so Cursor, Claude Code and Codex build features instead of re-deciding architecture. Start with 80% done.
heymrun/heym	★1,603	Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
davidondrej/cloudroom	★1,601	Cloud agents for any harness. Claude Code, Codex, Pi, and OpenCode run in isolated sandboxes, and live sessions move between your Mac and the cloud.
tddworks/ClaudeBar	★1,577	A macOS menu bar application that monitors AI coding assistant usage quotas. Keep track of your Claude, Codex, Antigravity ,and Gemini usage at a glance.
gastownhall/gascity	★1,511	Orchestration-builder SDK for multi-agent coding workflows
limecloud/lime	★1,494	Full-stack AI agent for coding, files, terminals, tools, research, content, multimodal work, and multi-agent workflows.
Dicklesworthstone/coding_agent_session_search	★1,203	Unified TUI and CLI to index and search your local coding agent session history across 30+ providers (Codex, Claude Code, Gemini, Cursor, Aider, Copilot, and more) into one searchable timeline. Hybrid search plus robot/JSON output for agents.
agentic-community/mcp-gateway-registry	★1,045	Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP server chaos into governed, auditable tool access with Keycloak/E
CopilotKit/aimock	★1,009	Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies.
pulseaiclub/phi	★1,002	A fast coding agent, rpc plugin, sub-agents, sloppy edits, and mcp
MichaelKinsy/PiG	★839	PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstream behavior is the contract, and Go is the implementation language.
Ark0N/Codeman	★838	Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemini CLI 24/7, from any device, watch every subagent live
termio-sh/termio	★788	A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative
nanocodexyz/nanocode	★702	SDK for Frontier Embedded Agents.
avibe-bot/avibe	★639	Make your computer a home for your AI partner. Avibe is the local-first Agent OS: Vibey, its built-in AI partner, works out of the box, and Claude Code, Codex & OpenCode run unchanged beside it — reach them from your browser, phone, or any chat app.
pixtuoid/pixtuoid	★556	Terminal pixel-art office for AI coding agents
ansible/vscode-ansible	★492	Ansible IDE extension: auto-completion and integrating quality assurance tools like ansible-lint, ansible syntax check, yamllint, molecule and ansible-test.
SourceWeft/SourceWeft	★450	Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure. Free to use GPT 6: https://SourceWeft.com/
marcusquinn/aidevops	★448	Vibe-Coding is easy. DevOps is hard. OpenCode & Git token-efficient AI agent automation for your app, business, and personal development. Opinionated tools, services, CLI & API stack for speed, security, and 24/7 results. Open-source first. SOTA everything. The best AI harness for GitHub & teamwork.
Tencent/LoopForge	★240	Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
dev-toolings/superpowers-symfony	★233	Claude Code plugin for Symfony 7.4 LTS & 8.x — 44 skills, 7 AI subagents & 13 commands for API Platform v4, Doctrine ORM 3, TDD (Pest/PHPUnit), Messenger, security & DDD.
boadij/pi-herdsman	★222	Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.
NeverSight/learn-skills.dev	★221	Curated high-quality AI Agent Skills. Search, install, copy and share. Works with Claude Code, Cursor, OpenClaw, and other AI coding tools.
zoefix/agent-speed	★203	Agent Speed — A lightweight, real-time token speed monitor for Codex and Claude Code. Track tokens per second (TPS), detect slowdowns, and monitor AI agent performance at a glance.
AIpRoBuilder/FlowX	★203	MCP server and Python SDK that generates, runs and refines AI agent workflows from natural language (Generative Workflow, A2A, FastAPI).
skaft-software/octet	★200	fast rust coding agent, extensible in any language, multimodal inputs, deep provider integrations.
shashankswe2020-ux/whoop-mcp	★181	Read-only WHOOP MCP server for recovery, sleep, HRV, strain, workouts, and personal health analytics in Claude, Codex, and GitHub Copilot.
EternalNight996/memory-eternal	★165	Your AI forgets every session. Give it a memory you can audit: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor, OpenClaw, Hermes and MengBot (any MCP client), with an immutable audit log and a token ledger. Agents propose, humans approve. MIT, self-hoste
dmae97/omk	★152	Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.
vibex-ai/vibex	★138	Your agents. Your workspace. Your control—from prompt to commit, desktop to mobile. Works with Codex, Claude Code, OpenCode, Pi, Grok, DeepSeek Harness, Antigravity, and many more through ACP.
mikecann/threadbear	★131	A Mac app for running your Claude Code and Codex threads, on the subscriptions you already have. Comes with an iPhone app, and you get all the source.
makifbaysal/tasktrooper	★122	Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollama, LM Studio), all on your own Pc
autopus-ai/autopus-adk	★109	Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.
ralforion/orionbelt-semantic-layer	★104	Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
amafjarkasi/electron-mcp-server	★102	MCP server for debugging Electron apps via Chrome DevTools Protocol. Start/attach processes, capture screenshots, read console errors & network logs, inspect DOM, evaluate JS, and automate UI — built for Cursor and other MCP clients.
wenlan-app/wenlan	★95	A living wiki your AI writes from your notes, code, AI chats (memories), and docs, checked against sources. It flags what it can’t back up and updates pages when sources change. Supports Claude, Codex, Obsidian...
cdeust/zetetic-team-subagents	★9	One epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block unsourced constants, vacuous tests and AI-writing patterns. I
Muratovnik/assay	★1	Evidence-grounded methods for coding agents: skills and agent profiles for Claude Code, Codex, Cursor and Gemini CLI

② Medical / clinical-research AI and agent skill libraries

Project	Stars	One-liner
scverse/scvi-tools	★1,724	Deep probabilistic analysis of single-cell and spatial omics data
hail-is/hail	★1,082	Cloud-native genomic dataframes and batch computing
cBioPortal/cbioportal	★1,065	cBioPortal for Cancer Genomics
FirelyTeam/firely-net-sdk	★942	The official Firely .NET SDK for HL7 FHIR
HL7/fhir	★764	Official source for the HL7 FHIR Specification
OpenChemistry/avogadrolibs	★704	Avogadro libraries provide 3D rendering, visualization, analysis and data processing useful in computational chemistry, molecular modeling, bioinformatics, materials science, and related areas.
chemosim-lab/ProLIF	★555	Interaction Fingerprints for protein-ligand complexes and more
pinellolab/CRISPResso2	★359	Analysis of deep sequencing data for rapid and intuitive interpretation of genome editing experiments
cqframework/clinical_quality_language	★339	Clinical Quality Language (CQL) is an HL7 specification for the expression of clinical knowledge that can be used within both the Clinical Decision Support (CDS) and Clinical Quality Measurement (CQM) domains. This repository contains complementary tooling in support of that specification.
DIAGNijmegen/rse-grand-challenge	★195	A platform for end-to-end development of machine learning solutions in biomedical imaging
Gaoyuan-0423/biomedical-paper-reader	★156	Biomedical paper-reading skill & local app: figure analysis, evidence appraisal, and research design insights. Chinese, English & bilingual reports.
David-OConnor/molchanica	★152	Protein and molecule viewer, editor, simulator
saezlab/corneto	★109	Unified knowledge-driven network inference from omics data
CMSgov/beneficiary-fhir-data	★87	An API designed to serve Medicare beneficiaries' demographic, enrollment, and claims data using the HL7® FHIR® Standard format.
didymo/OnkoDICOM	★73	OnkoDICOM was created with Radiation Oncologists to allow Radiation Oncologists to do research on DICOM standard image sets (DICOM-RT, CT, MRI, PET) using open source technologies, such as pydicom, dicompyler-core, PySide6, PIL, and matplotlib. OnkoDICOM is cross platform, open source software, and
camlab-bioml/rakaia	★73	Scalable spatial omics in the browser for hundreds of samples at once / 10x, IMC, IF, H&E, CosMX, & more / https://rakaia.io/
GenomicsStandardsConsortium/mixs	★65	Minimum Information about any (X) Sequence” (MIxS) specification
fulcrumgenomics/fgumi	★63	High-performance UMI tools for NGS data analysis
stjude/proteinpaint	★57	Data visualization and analysis framework focused on phenotype-molecular data integration at cohort level.
StatFunGen/xqtl-protocol	★57	Molecular QTL analysis protocol developed by ADSP Functional Genomics Consortium
microbiomedata/nmdc-schema	★53	National Microbiome Data Collaborative (NMDC) unified data model
HL7/US-Core	★50	FHIR R4 version of US Core IG
bioFAM/mofaflex	★50	factor models for omics data
molecule-dev/molecule	★44	Open-source, composable full-stack packages an AI can wire correctly. Swap any provider in one line. Export anytime.
virtool/virtool	★44	Viral infection diagnostics using next-generation sequencing
Victor-Xu-1/X-Science	★41	X-Science — an open-source biomedical research workspace. Apache-2.0 with component-specific third-party terms.
xinyuran/RLRefine	★12	Schema-driven LLM extraction with source-grounded validation, deterministic repair, and SFT → DPO → GRPO recipes.
genokeeper/genokeeper	★2	Local, privacy-first analyser for your own whole genome sequencing (WGS) data: FASTQ to GRCh38 calls with DeepVariant on your Mac, graded against ClinVar, gnomAD and ClinGen, with pharmacogenomics (PharmCAT, CPIC), polygenic scores, haplogroups and repeat expansions. Nothing leaves your machine unle
vxxqv/openomicsbench	★2	Offline RNA, DNA, protein, single-cell and genomic interval benchmarks with a five-assay demo and traceable reports.
Prabh54/groundedmed	★0	Research demo: agentic RAG that gives citation-checked answers to biomedical yes/no/maybe questions, refuses when evidence is weak, and publishes its results from a frozen 200-question PubMedQA test. Not medical advice.
zaidwhy/assay	★0	Multi-agent research system that checks every claim against the exact passage it cites, and abstains when the evidence is thin.
WannaBeSolopreneur/openevidence-guideline-tracker	★0	Live tracker of public clinical guideline and drug label changes, mapped to ICD-10 and RxNorm

③ Health management / nutrition and food AI

Project	Stars	One-liner
mealie-recipes/mealie	★13,875	Mealie is a self hosted recipe manager and meal planner with a RestAPI backend and a reactive frontend application built in Vue for a pleasant user experience for the whole family. Easily add recipes into your database by providing the url and mealie will automatically import the relevant data or ad
MichaIng/DietPi	★6,401	Lightweight justice for your single-board computer!
crbnos/carbon	★2,815	Open-source manufacturing ERP, MES and QMS. Quoting, MRP, inventory, shop floor, quality and lot/serial traceability on one Postgres schema, with a REST API and MCP server. Self-host or use Carbon Cloud.
vllm-project/recipes	★1,085	Common recipes to run vLLM
brandonp2412/Flex	★453	Offline-first workout tracker for strength and cardio, with progress graphs, rest timers, and custom themes. Built with Flutter.
1c7/Fitness	★410	Fitness instruction videos for fat loss, muscle gain, stretching and relaxation, warm-up, posture and rehabilitation (with many Bilibili and Douyin videos).
MichaIng/DietPi-Docs	★242	Source repository for the DietPi OS documentation
slimeglitch/gryffin-calorai-ventus	★114	Top AI Calorie Tracker GitHub 2026
Ajhar424/Senior-Fit-Flow	★56	Senior Fitness Tracker App 2026: Guided Home Workouts for Elderly Health
tsubotti63/garmin-running-data-normalizer	★11	Local-first Python CLI and local browser GUI that turn Garmin Account Data Export into reproducible running, FIT, sleep, HRV, and training datasets with QA and provenance.
cbukenya/healthier	★9	A self-hostable personal health dashboard for your Google Health data: sleep, HRV, activity and evidence-based insights.
MMacLean305/Vivacity	★3	Vivacity is a full-stack health and fitness application featuring workout tracking, nutrition logging, progress monitoring, and AI-powered exercise recommendations.
BoraErenErdem/pulse-coach	★2	A multi-agent AI health & fitness coach built with LangChain, FastAPI, and local LLMs (Ollama), featuring RAG-powered nutrition/exercise guidance and proactive check-ins.
GiovanniDelGaudio1994/forma-ai	★0	AI-powered fitness and nutrition app featuring personalized workout plans, adaptive coaching, progress tracking, exercise video analysis, and allergy-aware meal planning.
SyberKraken/morrowkeep	★0	Local-first daily planner for Windows: tasks, chores, meals, workouts, calories and weight. Rust + egui, lives in the tray.
AA-0324/meliusme	★0	A minimalist, privacy-focused nutrition and meal-tracker. Local-only data storage and zero friction. Built for accurate tracking and user ownership.
victoriacarbonell/nutri-app	★0	Calorie and nutrition tracker PWA with AI photo analysis · work in progress
mzaiger/FastFoodDiet	★0	An application that builds you a fast food meal diet plan for 7 days with a calorie input. This is to help you stay within the calories you have for a goal each week.
ShamsahAld/Microbiome_Fermented	★0	Analyse metagenomic data from populations consuming traditional fermented foods (kefir, kombucha, Arabian laban) and construct microbial co-occurrence networks. Identify which microbial modules are enriched and link them to host metabolic pathways using network topology.
mariogiordano96/plico	★0	Open source Android app for workout tracking, meal planning and nutrition. Italian CREA food data, guided workouts, optional AI coach. No account, no ads.
sajedayad/Forge	★0	Forge: a mobile-first gym and nutrition tracker built with Claude. Workout logging, calorie and protein tracking, photo label scanning, sleep insights and weekly check-ins.
shubhampawar05/nutrikit	★0	Self-hostable nutrition API: food search, portion-aware nutrients, meal logging from text, voice, photos, barcodes and labels, meal plans and an AI nutrition advisor. JS SDK on npm (@nutrikit/sdk).
Maheshdasi/FitPlate	★0	AI Fitness & Nutrition Platform: explainable calorie targets, ML meal and workout recommendations, progress tracking and weekly insights. React, FastAPI, PostgreSQL, scikit-learn.
binDebug3/Nutrition_Planner	★0	An app for dietetics students to automatically build meals based on nutrient needs
sumaisa-mou/calorie-whisperer	★0	AI-powered fitness and nutrition tracker: snap a meal photo, type what you ate, or chat to log food and workouts.
chetan-tomar03/NutriScan-AI	★0	AI-powered nutrition analysis app that identifies food from images and estimates calories, protein, carbs, fats, and fiber
gemivnet/fitsheet	★0	Personal fitness companion — calories, weight, workouts, walks, recipes, notes, analytics. Web PWA + API in one Docker image.
tebl22/don-bolon	★0	🧀 Snap your plate, get the truth. AI nutrition coach for Android: photo calorie tracking, science-based goals, fasting and a grumpy cheese-ball mascot.

④ Model foundation and agent infrastructure

Project	Stars	One-liner
netdata/netdata	★81,359	The fastest path to AI-powered full stack observability, even for lean teams.
grafana/grafana	★77,825	The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
hiyouga/LlamaFactory	★75,988	Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
deepspeedai/DeepSpeed	★43,319	DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
facebookresearch/faiss	★41,375	A library for efficient similarity search and clustering of dense vectors.
servo/servo	★38,458	Servo aims to empower developers with a lightweight, high-performance alternative for embedding web technologies in applications.
seaweedfs/seaweedfs	★36,013	SeaweedFS is a distributed storage system for object storage (S3), file systems, Iceberg table buckets, and Lance vector buckets, designed to handle billions of files with O(1) disk access and effortless horizontal scaling.
apify/crawlee	★26,415	Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headf
longbridge/gpui-kit	★20,287	Rust GUI components for building fantastic cross-platform desktop application by using GPUI.
NVIDIA-NeMo/Speech	★18,727	A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
NVIDIA/Megatron-LM	★18,373	Ongoing research training transformer models at scale
modelscope/ms-swift	★16,081	Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
facebookresearch/sam3	★12,262	The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Arize-ai/phoenix	★12,238	AI Observability & Evaluation
lancedb/lancedb	★11,876	Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
storytold/vectorcraft	★11,602	VectorCraft: An open-source vector art tool written from scratch in pure Rust
ClickHouse/ClickStack	★10,020	Resolve production issues, fast. An open source observability platform unifying session replays, logs, metrics, traces and errors powered by ClickHouse and OpenTelemetry.
NVIDIA/cudf	★9,799	cuDF - GPU DataFrame Library
LearningCircuit/local-deep-research	★9,560	~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
flyteorg/flyte	★7,833	Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference on your k8s — in pure Python with async/await, also other languages (rust, go and ts)
OneUptime/oneuptime	★7,810	Complete open-source monitoring and observability platform.
getopenscreen/openscreen	★6,879	Record your screen, ship a demo. Free and open-source, GPU-accelerated, no watermarks, no subscriptions. Windows, macOS, Linux. Actively maintained.
skyzh/tiny-llm	★5,712	learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
ModelTC/LightLLM	★4,359	LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
uxlfoundation/oneDNN	★4,091	Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
checkpoint-restore/criu	★4,066	Checkpoint/Restore tool
NVIDIA/cuda-rust	★4,023	NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
HakanSeven12/OpenCADStudio	★3,972	A CAD application built with Rust — 2D/3D drawing, DWG/DXF support, and GPU-accelerated rendering
pytorch/TensorRT	★3,021	PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
thu-pacman/chitu	★2,999	High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
NVIDIA/gpu-operator	★2,980	NVIDIA GPU Operator creates, configures, and manages GPUs in Kubernetes
mw00/project-maya	★2,766	Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.
jolibrain/deepdetect	★2,551	Deep Learning Server and CLI for Torch and TensorRT
noonghunna/club-3090	★2,490	Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/
lupinemachines/lupine	★2,463	LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
ovg-project/kvcached	★2,038	Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
SemiAnalysisAI/InferenceX	★2,022	Open Source AI Accelerator Research Platform Standard.
CrossGL/crosstl	★1,989	Translate GPU shaders and compute kernels between GLSL, HLSL, Metal, SPIR-V, Slang, CUDA and HIP, and to WGSL, through the CrossGL IR
datawhalechina/zero-to-sglang	★1,976	Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
AdamPlatin123/dsh-plugin-radar	★1,500	DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact.
alibaba/rtp-llm	★1,394	RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
ModelCloud/GPTQModel	★1,289	LLM model quantization (compression) toolkit with HW acceleration support for Nvidia (CUDA), AMD (ROCm), Intel GPU (XPU), Huawei Ascent (NPU), and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
sgl-project/SpecForge	★1,279	Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
CurvineIO/curvine	★1,058	AI-native, cloud-native file system in Rust. Full POSIX on object storage with a multi-tier distributed cache, for AI training, inference, and agents. CNCF Sandbox project.
kividbio/kividb	★1,057	A fast, multi-threaded Redis® and Valkey alternative written in Rust: drop-in compatible, with full-text and vector search built in
NVIDIA/cudnn-frontend	★996	cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
livekit/agents-js	★962	Build realtime multimodal AI agents with Node.js
openvinotoolkit/model_server	★956	A scalable inference server for models optimized with OpenVINO™
synchopate/llama-modchip	★897	🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
ai-dynamo/aiperf	★866	AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
TrenTorch/TrenTorch	★835	Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
usemoss/moss	★806	The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.
Helldez/BigMoeOnEdge	★741	Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
pegainfer-project/pegainfer	★739	Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
nace-ai/kapitsa	★732	Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
Basekick-Labs/arc	★690	Open, SQL-native time-series database for telemetry you need to keep. 38M+ records/sec ingestion, 25M+ rows/sec queries. InfluxDB Line Protocol and Telegraf compatible. Open Parquet on your storage. Single binary. S3/Azu
zhongkaifu/TensorSharp	★671	A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows
chainloop-dev/chainloop	★611	Agentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs
kacper-daftcode/vLLM-Moet	★572	Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0
alchemy-run/distilled	★522	Effect-native SDKs for cloud providers
bytedance/vArmor	★516	vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and NetworkProxy technologies to enforce access control from system calls to application protocols — protecting workloads including AI Agents.
vllm-project/vime	★503	An LLM post-training framework with vLLM for RL Scaling
volcano-sh/kthena	★497	Lightweight, Modular, Kubernetes-native AI serving platform for scalable model serving.
openxla/tokamax	★329	Tokamax: A GPU and TPU kernel library.
ai-dynamo/aitune	★290	NVIDIA AITune is an inference toolkit designed for tuning and deploying Deep Learning models with a focus on NVIDIA GPUs.
OrbitInfra/OrbitKV	★281	OrbitKV is a KV cache for vLLM and SGLang.
dsx-ai-factory/nvcf	★265	Platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.
adventists-ai/sophon-realtime	★227	Sophon-Realtime v1: open full-duplex voice models that hear your tone and speak with one. Tag and Flash run on one GPU with vLLM-Omni; E2E in preview.
sgl-project/sgl-kernel-npu	★200	SGLang kernel library for NPU
NVIDIA/kumo-engine	★75	Kumo Engine is an accelerator for context generation over structured data, designed for teams building and running predictive models in production at scale.
sgl-project/sgl-kernel-xpu	★38	SGLang kernel library for Intel XPU
intel/enterprise-ai-solutions	★11	Production-ready platform for deploying OpenAI-compatible LLM inference on Kubernetes. A one-command installer for enterprise generative AI on Intel® Xeon®, with vLLM and other serving engines, secure Keycloak authentication, and built-in o
intel/enterprise-inference	★8	Enterprise-grade, high-performance LLM serving on Kubernetes. OpenAI-compatible inference powered by vLLM and OpenVINO™ Model Server behind a unified AI gateway, with NUMA-aware CPU optimization for Intel® Xeon® - production model serving,

3. Trends today

⭐⭐⭐ "Did you actually read it" is becoming a question a machine can fail. On 11-10 I noted astryx reporting named scenarios rather than line numbers, and on 11-09 I noted squad aligning spec, docs and matrix with the code plus regression guards. Today assay takes that idea all the way onto the agent itself: tie a read claim to every file its sentence lists — when the model says "I read this file", it must produce a complete list, and every name in that list must have a matching Read. My expert-package QC is still "ask the model to grade itself"; this whole mechanism is copyable.
⭐⭐⭐ "Pinning a conclusion to its source material" now has three different implementations. groundedmed has a critic model check each finding against the original abstract; openomicsbench freezes decision rules together with checksums into an installable package; chainloop makes "which skill was loaded" an auditable event in its own right. Three stacks with nothing in common, all answering the same question — three months from now, how do I know how that report was actually produced? My GRPM to-do from 11-09 only solves half of it: the fields are there, but which rule set and which raw data produced a given conclusion is still untraced.
⭐⭐ The dividing line in the health line: database semantics versus photo calorie counting. Most of this issue's 28 health entries are still "photograph the meal, count the calories", while nutrikit works on aligning food names to nutrient-database identifiers — the dal makhani to black gram fix is a wall only someone running this in production would hit. The point is that the hard part of nutrition AI is not recognition, it is alignment. What stalls me in supplement formulation and functional-medicine assessment is exactly this layer. The self-hostable + MCP combination also lines up directly with my GLP-1 nutrition companion's integration needs.
⭐⭐ The dsh ecosystem keeps showing up. AdamPlatin123/dsh-plugin-radar (★1,500, 238 commits in the window) is an open-source ecosystem radar that continuously snapshots and renders changes across the dsh plugin ecosystem — I run dsh locally, so this line deserves persistent priority. Last issue had four dsh extensions from four different teams on the board at once (dsh-Go, dsh-blender-plugin, dsh-mnemon, dsh-memory), which says this is no longer one person's project but an ecosystem that has formed.
⭐⭐ Licensing this round produced a fresh three-tier sample. Genuinely open source (MIT and Apache-2.0 together, 128 entries, 66%; 146 entries once BSD / ISC / MPL and other permissive terms are included, 75%), source-visible but not open source (orionbelt-semantic-layer on BUSL-1.1, phoenix on ELv2, TrenTorch on PolyForm NC), and not open at all (forma-ai and meliusme proprietary, rakaia all-rights-reserved, CRISPResso2 academic non-commercial — 4 entries). For a one-person company these are still three different things: the third tier cannot even be read, the second can be read and studied but must never become a product dependency, and only the first tier is a selection candidate. The sharpest detail this round: two pick repositories (groundedmed and nutrikit) have no LICENSE file at all — their methodology is worth copying, but their code cannot be depended on directly.

4. Repo index

GitHub AI Daily · 2026-11-11 (Wednesday)

1. Today's picks (5)

1. Prabh54/groundedmed: A biomedical RAG agent that has to prove it did not make anything up

2. Muratovnik/assay: A gate that forces coding agents to list every file they actually read

3. vxxqv/openomicsbench: A locally runnable answer to "how do you validate omics software?"

4. shubhampawar05/nutrikit: A self-hostable nutrition API with an MCP server — and it fixed a real-world food-matching gap

5. chainloop-dev/chainloop: Turning "what the AI wrote" into an auditable trace

2. Category roundup

① AI Coding / coding agents and the skill ecosystem

② Medical / clinical-research AI and agent skill libraries

③ Health management / nutrition and food AI

④ Model foundation and agent infrastructure

3. Trends today

4. Repo index