AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
AI agent toolkit for coding agents, unified LLM APIs, agentic workflows, tool harness and more.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Toolkit for building AI agents.
The curiosity for building was inspired by by the great work of Mario Zechner on Pi-Mono.檢視完整 README ↗An open-source coding agent for code & work: run sessions in your repo or an isolated sandbox, on any model, extended with plugins.
curl -fsSL https://codework.sh/install | sh
Or with Node.js 24+: pnpm add -g @codeworksh/cli.
export OPENAI_API_KEY=...
codework run --provider openai --model gpt-6-luna "Inspect and fix the failing tests"
export ANTHROPIC_API_KEY=...
codework run --provider anthropic --model claude-sonnet-5-5 "Inspect and fix the failing tests"
List every provider and model with codework models.
codework models).codework auth login --openai-codex or --github-copilot.daytona, vercel, memory, or sqldb sandboxes.codework serve owns sessions and sandboxes; clients attach with --server.codework plugin add <pkg> adds tools, prompts, and sandbox drivers, per project or globally (-g).See the docs for every command and flag.
| Package | Description |
|---|---|
@codeworksh/cli | The codework coding agent CLI. |
@codeworksh/harness | Effect-powered agent runtime with persistent sessions and sandboxes. |
@codeworksh/plugin | SDK for tools, prompt plugins, and sandbox drivers. |
@codeworksh/aikit | Unified multi-provider LLM API with streaming, tools, and usage. |
Requires Node.js 24.14.1+ and pnpm.
git clone https://github.com/codeworksh/codework.git
cd codework
pnpm install
pnpm cli -- --help # run the CLI from source
pnpm exec vp check
pnpm exec vp run typecheck
Read AGENTS.md for repository conventions, and open an issue for bugs or ideas.
The curiosity to build this project was inspired by Mario Zechner’s work on Pi-Mono.