coccinella-labs 开源 C++20 终端 AI 编程智能体 agentware

A C++20 AI coding agent that runs in your terminal. It talks to hosted model providers, reads and edits code through MCP filesystem and git servers, and works offline against local models.

cmake -S . -B build -DCMAKE_BUILD_TYPE=Release
cmake --build build
./build/bin/agentware-agent

On first run it prints a welcome screen and asks for a mode: online against a hosted provider, or offline against a local model.

Providers

Nine agent modes, one per provider or model family: Together, Llama 3B, Cerebras, Llama Latest, Llama 3.1, Fireworks, Groq, DeepSeek, and OpenAI. Each hosted mode needs its API key in the environment; see .env.example for the list. The three Llama modes and Offline run against a local Ollama server and need no key.

What it does

Around twenty services behind one binary: agent orchestration, AI provider calls, auth, checkpoints, codebase search, command execution, configuration, context tracking, a database layer, file and multi-file operations, git and GitHub integration, MCP client support, memory management, sandboxing, theming, input validation, and a web service.

Codebase search shells out to rg and fd when they are on PATH and falls back to a built-in scanner when they are not, so search works either way. github:threads:owner/repo:pr reads inline review threads without the GraphQL API.

Model Context Protocol servers are configured in data/mcp_servers.json. Two ship by default, both run through npx: a filesystem server rooted at the working directory and a git server.

Scope

src/ holds the implementation, public headers under src/include/, tests under src/tests/, and automation under src/scripts/. CMakeLists.txt and Makefile both build the same targets; make wraps the CMake invocation.

Releases

Merging to main bumps the version, tags it, and creates a GitHub release automatically. Binaries are attached by a separate build workflow that runs on the tag push.

That separation has one requirement worth knowing: tags and releases created with GITHUB_TOKEN do not trigger new workflow runs, so the build never sees them and the release stays empty. The version-bump job therefore prefers a RELEASE_TOKEN secret (a personal access token with contents write access) and falls back to GITHUB_TOKEN with a warning. Without that secret, every automated release ships with no binaries, which is what happened to the releases that prompted this note.

To backfill a release, run the Release workflow by hand against its tag from the Actions tab.

Tests

cmake --build build --target test

ctest runs two targets. basic_tests is the unit suite, currently 50 cases across 16 suites, covering parsing, file-access policy, project-root discovery, MCP and GitHub availability, review threads, memory persistence, input validation, and both search backends. remediation_probes is a shell harness that drives the built binary against known-bad input and asserts it refuses.

CI additionally runs a build matrix, coverage, lint, Docker end-to-end, and release jobs. Nothing in either target exercises the agent against a live model. The e2e job needs Docker; the coverage job needs its toolchain installed.

Contributing

CONTRIBUTING.md is the authority, not this file. External contributions are not accepted at this time; the project is maintained by collaborators. If that changes, the contributing guide will say so first.

License

MIT. See LICENSE.