{"id":"juyterman1000-entroly","name":"entroly","homepage":"https://pypi.org/project/entroly/","repo_url":"https://github.com/juyterman1000/entroly","category":"ai-ml","subcategories":[],"tags":["ai-coding","context-engineering","mcp","proxy","token-optimization","rag-alternative","local-first","python"],"what_it_does":"Entroly is a context engineering/optimization tool for AI coding agents. It ingests and indexes a workspace, scores/selects and compresses codebase context to fit within token budgets, and delivers that optimized context to agents via an MCP server or a local HTTP proxy. It also provides a dashboard/metrics, explain endpoints, and optional reinforcement-learning-style weight adjustment from feedback.","use_cases":["Improve code-generation quality for IDE-integrated coding agents by supplying more relevant context within token limits","Reduce token/cost usage for agent-based coding workflows","Support multiple agent providers/tools (Cursor/Claude Code/Copilot/Windsurf/OpenClaw and others via proxy)","Provide codebase health/security scanning signals and context explanations for debugging agent behavior","Run local context optimization with optional native acceleration"],"not_for":["Use as a general-purpose embeddings/RAG service for end-user search without codebase optimization goals","Scenarios requiring fine-grained enterprise auth/tenant isolation guarantees (not evidenced here)","Environments where running a local proxy/MCP server is not permitted"],"best_when":"You want local, IDE-agent-friendly context optimization across an entire repository, especially when agents only see a small subset of files.","avoid_when":"You cannot expose localhost endpoints to your agent tool, or you need a documented, standards-based API contract (OpenAPI) with strong security controls beyond local dev defaults.","alternatives":["Custom RAG pipelines (vector search + chunking)","Repo-level prompt/context builders (manual curation)","Dedicated context services/proxy frameworks for LLM tooling","Open-source code indexing + retrieval systems (e.g., tree-sitter + custom retrieval)","Vendor-specific MCP/RAG integrations"],"af_score":51.5,"security_score":30.2,"reliability_score":32.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:50:04.742420+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Localhost integration via MCP (tool registration)","Local HTTP proxy on localhost (no auth described in README)"],"oauth":false,"scopes":false,"notes":"No authentication scheme, tokens, or scope model is described for the proxy/MCP endpoints in the provided README/manifest snippet; it appears to be intended for local use (localhost)."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Pricing not described in provided content; as a Python package, primary cost is infrastructure/local runtime and optional native acceleration dependencies."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":51.5,"security_score":30.2,"reliability_score":32.5,"mcp_server_quality":55.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":5.0,"tls_enforcement":20.0,"auth_strength":25.0,"scope_granularity":10.0,"dependency_hygiene":60.0,"secret_handling":45.0,"security_notes":"The tool performs local SAST/security scanning (55 rules) as a feature claim, but provided content does not include security controls for the proxy/MCP endpoints (e.g., authentication/authorization, CSRF protections, TLS requirements). Because it is likely localhost-focused, TLS/encryption and auth are unclear. Secret handling practices are not evidenced in the provided README/manifest snippets.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":20.0,"error_recovery":65.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Proxy endpoints are described as localhost services; agents must be configured to point to the correct base URL (e.g., http://localhost:9377/v1)","Port conflicts can occur (README mentions 9377 already in use)","MCP/IDE integration relies on `entroly init` generating appropriate config/artifacts (e.g., .cursor/mcp.json for Cursor)","Rust engine may not load; falls back to Python if native wheel/tooling unavailable"]}}