# Entroly

> Entroly is an open-source, local-first context-control plane for AI coding agents. It selects and compresses repository context under explicit token budgets, can produce receipts for selection decisions, can preserve source recovery through CCR handles, and offers evidence-grounding audits for model output.

Primary install: `pip install entroly`

Start in a repository with `entroly go`. Run `entroly verify-claims` for a bounded local installation smoke test.

Indexing, selection, compression, receipts, and CCR storage run locally. When enabled, default WITNESS checks also run locally. Proxy mode still sends the selected prompt to the user's configured LLM provider. No outbound analytics are enabled by default.

Savings depend on repository size, workload, token budget, provider, and baseline. WITNESS evaluates support against supplied evidence; it does not establish universal truth. Default proxy mode audits output, while strict mode can suppress unsupported claims.

Best fit: repeated AI-agent work over medium or large repositories, especially where token budgets, recoverability, and audit records matter.

Weak fit: short prompts, tiny repositories, or workflows requiring byte-for-byte unchanged context.

## Start Here

- [Repository and quick start](https://github.com/juyterman1000/entroly): Installation, CLI usage, architecture, and measured results.
- [Documentation](https://juyterman1000.github.io/entroly/): User guides and integration documentation.
- [Python package](https://pypi.org/project/entroly/): Primary CLI, proxy, MCP, and Python SDK distribution.
- [Limitations](https://github.com/juyterman1000/entroly/blob/main/docs/limitations.md): Explicit constraints and non-guarantees.

## Verification And Evidence

- [Packaged verifier](https://github.com/juyterman1000/entroly/blob/main/entroly/verify_claims.py): Bounded SDK, indexing, budget, synthetic recovery, and engine smoke checks.
- [Benchmark artifacts](https://github.com/juyterman1000/entroly/tree/main/benchmarks/results): Workload-specific measurements and reports.
- [WITNESS implementation](https://github.com/juyterman1000/entroly/blob/main/entroly/witness.py): Evidence-grounding analysis and output policies.
- [STAVE implementation](https://github.com/juyterman1000/entroly/blob/main/entroly/verifiers/stave.py): Deterministic structural checks used by the default verifier.
- [Context receipt example](https://github.com/juyterman1000/entroly/blob/main/docs/examples/context_receipt.md): Human-readable record of context decisions.

## Interfaces

- [MCP package](https://www.npmjs.com/package/entroly-mcp): NPX bridge for MCP clients.
- [Node and WASM package](https://www.npmjs.com/package/entroly): Compatibility alias for the Node and WASM runtime.
- [Team and security guide](https://github.com/juyterman1000/entroly/blob/main/docs/for-teams.md): Deployment, security, and evaluation guidance.
