{"data":{"slug":"juyterman1000-entroly","name":"entroly","tagline":"Local context-control plane for AI coding agents: select evidence, compress recoverably, keep caches hot, and verify answers. MCP/proxy/SDK for Cursor, Claude Code, Codex, and Aider.","github_url":"https://github.com/juyterman1000/entroly","owner":"juyterman1000","repo":"entroly","owner_avatar_url":"https://avatars.githubusercontent.com/u/208309368?v=4","primary_language":"Python","stars":420,"forks":66,"topics":["ai","ai-agents","ai-hallucination","anthropic","chatgpt","claude","claude-code","context-compression","cursor","hallucination-detection","llm","llm-grounding","mcp","mcp-server","open-source","productivity","rag","rust","token-optimization"],"archived":false,"github_pushed_at":"2026-07-11T23:24:45+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/juyterman1000-entroly","markdown_url":"https://www.graphcanon.com/tools/juyterman1000-entroly.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/juyterman1000-entroly","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=juyterman1000-entroly","description":"Local context-control plane for AI coding agents: select evidence, compress recoverably, keep caches hot, and verify answers. MCP/proxy/SDK for Cursor, Claude Code, Codex, and Aider.","homepage_url":"https://juyterman1000.github.io/entroly/docs/dashboard.html","license":"Apache-2.0","open_issues":2,"watchers":5,"ai_summary":null,"readme_excerpt":"

\n 中文 •\n 日本語 •\n 한국어 •\n Português •\n Español •\n Deutsch •\n Français •\n Русский •\n हिन्दी •\n Türkçe\n

\n\n

\n \"Entroly\"\n

\n\n

Know exactly what your AI agent saw.
\nEntroly creates replayable Context Commits: content-addressed proof of the evidence selected, omitted, and kept recoverable for each model request.

\n\n

\n Drop-in for Cursor, Claude Code, Codex, Aider + 34 more and custom providers — 60s, no code changes.\n

\n\n

\n Auditable context control plane · every answer gets a receipt: what was used, what was omitted, why, and the risks that remain · local-first · Rust + WASM · reversible · savings measured on real workloads\n

\n\n

\n \"PyPI\"\n \"npm\"\n \"GitHub\n \"Discord\"\n \"License\"\n \"Token\n \"Hallucination\n \"Rust\n \"Context\n

\n\n

\n pip install -U entroly && cd /your/repo && entroly verify-claims && entroly simulate\n

\n\n

\n Get started ·\n Proof ·\n Integrations ·\n What's inside ·\n Architecture ·\n For teams ·\n Limitations\n

\n\n

\n \"Live\n  \n \"Dashboard\"\n

\n\n

\n Deciding whether to star? Run the no-key proof first: entroly verify-claims && entroly simulate.
\n If it finds meaningful savings or gives you auditable receipts on your repo, star it so other agent builders can find it. If it does not, open an issue with the verification JSON.\n

\n\n---\n\n## What it does\n\nEntroly is an auditable context control plane for AI agents. It decides what context to send, records what it left out, and produces a receipt you can inspect before trusting a hard multi-file answer.\n\nMost compression tools shrink whatever text the agent already chose. Entroly starts one step earlier: it chooses the highest-value evidence first, compresses only after selecti","github_created_at":"2026-03-07T23:03:02+00:00","created_at":"2026-07-11T23:37:01.590294+00:00","updated_at":"2026-07-11T23:37:08.964267+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"}],"tags":[{"slug":"ai-hallucination","name":"ai-hallucination"},{"slug":"ai","name":"ai"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"claude","name":"claude"},{"slug":"claude-code","name":"claude-code"},{"slug":"anthropic","name":"anthropic"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"context-compression","name":"context-compression"}],"trust":{"provenance":{"is_fork":false,"github_id":1175591394,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T23:37:04.270Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-07-11T21:23:06Z"},"security_summary":{"status":"findings","scanner":"mcp_manifest@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:37:04.824Z","medium_count":1,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-07-11T23:37:03.991Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-07-11T23:37:03.991Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-11T23:37:03.991Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-07-11T23:37:03.991Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-11T23:37:03.991Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-11T23:37:03.991Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-11T23:37:03.991Z"}}}}