{"data":{"slug":"juyterman1000-entroly","name":"entroly","tagline":"Know exactly what your AI agent saw.","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":471,"forks":71,"topics":["agent","ai-agents","ai-coding-agents","claude-code","codex","context-compression","context-engineering","context-optimization","context-window","developer-tools-ai-agent","github-copilot","graph","hallucination-detection","harness-engineering","llm","loop-engineering","mcp","openclaw","token-optimization","tokenomics"],"archived":false,"github_pushed_at":"2026-10-02T08:27:18+00:00","maintenance_label":"Very active","stars_delta_30d":38,"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":"Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.","homepage_url":"https://juyterman1000.github.io/entroly/docs/index.html","license":"Apache-2.0","open_issues":1,"watchers":7,"ai_summary":"Local context-control plane for AI coding agents that manages evidence selection, compresses and keeps caches hot, verifies answers, and serves as an MCP/proxy/SDK for Cursor, Claude Code, Codex, and Aider among others.","readme_excerpt":"## Install\n\n> **Not sure which one?** Pick **Python**. It's the complete version and what\n> most people use. The others are alternate ways to run the same engine.\n| Platform | Install | What you get |\n|---|---|---|\n| 🐍 **Python** (pip) — *recommended* | `pip install -U entroly` | Everything: the command-line tool, the server your AI editor talks to, and the code library |\n| 📦 **Node / npm** | `npm install -g entroly` | The same engine, nothing Python required |\n| 🦀 **Rust** (source build) | `cd entroly-core && cargo build --release --bin entroly-rs --features proxy` | One self-contained program, no Python or Node needed |\n| 🍺 **Homebrew** | `brew install juyterman1000/entroly/entroly` | The command-line tool on macOS/Linux |\n| 🐳 **Docker** | `docker pull ghcr.io/juyterman1000/entroly:latest` | Runs in a container, nothing installed on your machine |\n\n**Prefer a package runner instead of a global install?** These commands use\nthe same published artifacts in an isolated tool cache:\n\n```bash","github_created_at":"2026-03-07T23:03:02+00:00","created_at":"2026-07-11T23:37:01.590294+00:00","updated_at":"2026-10-03T06:00:19.891341+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":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"context-compression","name":"context-compression"},{"slug":"hallucination-detection","name":"hallucination-detection"},{"slug":"token-optimization","name":"token-optimization"}],"trust":{"provenance":{"is_fork":false,"github_id":1175591394,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-03T06:00:19.082Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-24T15:26:41Z","stars_delta_30d":38,"open_issues_delta_30d":-5},"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":"2026-10-03T06:00:19.540Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-10-03T06:00:19.540Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-10-03T06:00:19.540Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-10-03T06:00:19.540Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-10-03T06:00:19.540Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-10-03T06:00:19.540Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-10-03T06:00:19.540Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you require proof of evidence selection to ensure transparency in model decisions, use Entroly.","Use Entroly when working on projects that demand context-control and auditing across multiple coding agents like Cursor or Claude Code."],"when_not_to_use":["Avoid using Entroly if your AI workflows are already finely optimized for minimal intervention and do not benefit from additional context management layers.","Do not use Entroly if you have no need for replayable Context Commits, which Entroly offers to trace evidence selection and omissions."],"source":"enrich:decision_facts","observed_at":"2026-07-17T06:19:01.985Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Know exactly what your AI agent saw with Entroly."}]}}