自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
Turn any tutorial video into a verified, installable AI-agent skill. Reads the screen, not the transcript. Runs locally. MIT.
Measure and explain performance: web pages, Electron apps, Bun/Node, any process. Agent-native CLI + MCP.
TranslatedLocal-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health
Keyboard-first AI browser for macOS — WebKit + Rust, built-in AI sidebar, isolated workspaces, and an MCP server that lets your agents drive the web.
A self-hostable Git server for agent-scale traffic: packs in object storage, per-branch history in Postgres. Pre-alpha.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.