Local context OS for AI coding agents: token optimization, MCP tools, receipts, exact recovery, verification, and SDK helpers.
Project description
Know exactly what your AI agent saw.
Entroly is a local context control plane for AI coding agents. It selects the highest-value evidence under a token budget, records what was selected and omitted, keeps compressed context recoverable, and produces verifiable Context Commits and receipts.
Install
pip install -U entroly
Run the local, no-key verification path:
entroly verify-claims
entroly simulate
MCP server
Start the stdio MCP server directly:
entroly serve
Or use a package runner:
uvx --from entroly entroly serve
npx -y entroly-mcp serve
Entroly works with GitHub Copilot in VS Code, Claude Code, Cursor, Windsurf, Cline, Continue, Zed, and other MCP-compatible clients.
GitHub Copilot / VS Code
Create .vscode/mcp.json:
{
"servers": {
"entroly": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "entroly", "entroly", "serve"]
}
}
}
Or install through the MCP gallery after the official registry listing becomes available by searching for Entroly.
Claude Code
claude mcp add entroly -- uvx --from entroly entroly serve
Generic MCP configuration
{
"mcpServers": {
"entroly": {
"command": "uvx",
"args": ["--from", "entroly", "entroly", "serve"]
}
}
}
What Entroly adds
- Context selection under explicit token and cost budgets
- Context Commits linking selected, omitted, and recoverable evidence
- Context Receipts for replay, audit, and omission explanations
- Exact recovery of compressed fragments through stable handles
- Local verification through WITNESS and receipt checks
- Context Check coverage evidence for changed files and CI risk gates
- Rust and WASM engines with a pure-Python fallback
- Local-first operation with no outbound analytics by default
Links
- Repository: https://github.com/juyterman1000/entroly
- Documentation: https://juyterman1000.github.io/entroly/
- PyPI: https://pypi.org/project/entroly/
- npm MCP bridge: https://www.npmjs.com/package/entroly-mcp
MCP Registry identity
mcp-name: io.github.juyterman1000/entroly
Apache-2.0 licensed.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file entroly-1.0.52.tar.gz.
File metadata
- Download URL: entroly-1.0.52.tar.gz
- Upload date:
- Size: 18.1 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e8bb9d5050d200fe7deb3335828d6ef5a0389c8b8894ce70f30932a7005fdd81
|
|
| MD5 |
c22dde57e76eda0725f3bbe1927e1c44
|
|
| BLAKE2b-256 |
7fcb839cbf8bdc6d87f840b57e34875ff15823cd7e3d347b5b81f126445f07ee
|
File details
Details for the file entroly-1.0.52-py3-none-any.whl.
File metadata
- Download URL: entroly-1.0.52-py3-none-any.whl
- Upload date:
- Size: 1.0 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
08e80b79e071f7781a307f68c6cbdb3c1757ba2b9e8a0ac8080d55ef765fe7ca
|
|
| MD5 |
514f2018520c5681203420ed9ea5c679
|
|
| BLAKE2b-256 |
b5cf185a0bbfc3b5bbc525c0b71c6b98ef8430de914ef373d9c305e59919f8e3
|