Skip to main content

CLI for the Chinchill agent framework — scaffold a durable AI agent project with `chinchill init`

Project description

chinchill

The CLI for Chinchill — an open framework for building durable AI agents your team can talk to everywhere they already work (Slack, Microsoft Teams, GitHub, MCP clients, or plain HTTP), with persistent workspaces, file-based skills, sandboxed code execution, and human-in-the-loop approvals built in.

Scaffold an agent project

uvx chinchill init my-agent
cd my-agent
docker compose up          # then open http://127.0.0.1:8080/dev/chat-ui

chinchill init emits a small pack project you own — the agent's persona as editable Markdown, a tools/ folder where every public Python function becomes an agent tool, a connections/ folder that compiles OpenAPI specs into tools, and a docker-compose file that runs the framework as a container image behind it. No dependencies beyond the standard library.

Other subcommands (chinchill eval, for running behavioral eval datasets against your agent) run inside a framework environment — see the framework repository and its CLI reference.

Licensed under Apache-2.0.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

chinchill-0.1.0.tar.gz (13.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

chinchill-0.1.0-py3-none-any.whl (15.1 kB view details)

Uploaded Python 3

File details

Details for the file chinchill-0.1.0.tar.gz.

File metadata

  • Download URL: chinchill-0.1.0.tar.gz
  • Upload date:
  • Size: 13.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.14 {"installer":{"name":"uv","version":"0.9.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for chinchill-0.1.0.tar.gz
Algorithm Hash digest
SHA256 cad96f1dad229fd80dab0d17d7e395f4f047d0891901b02ec0ac5bcccae2bea2
MD5 6cf548c2d20e46ef5a0397880217ca95
BLAKE2b-256 dde325c02d06604d67ad757bb60f58d905bb7227dd64d1b1dcfed93107fdcdb0

See more details on using hashes here.

File details

Details for the file chinchill-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: chinchill-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 15.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.14 {"installer":{"name":"uv","version":"0.9.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for chinchill-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9c5d8a012825e00fb294de347341e40b109eda97dfb663a8bcddbef054a75184
MD5 709a80d0a234bc22abee58ed5969b475
BLAKE2b-256 5e2a5386639774d9406d4aa369b3a07b78caee78363e21ea61e9e0f4361bffd9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page