#ai-agents

Terminal-native AI coding agent running in containers.

Git-native context engineering CLI and MCP server for AI coding agents. Keep specs, ADRs, rules, plans, and project knowledge in Git.

AI-native TypeScript 3D SDK for browser 3D apps, prompt-to-code scenes, GLB/glTF product viewers, WebGL/WebGPU, Vite templates, diagnostics, and deploy checks.

An email client for AI agents. Filtered, read-only Gmail delivered to disk as .eml + markdown, and served over MCP.

Search EU legislation, CJEU case law, and treaties; traverse the CELLAR relationship graph; resolve EuroVoc concepts via MCP. STDIO or Streamable HTTP.

Rust toolkit for building LLM agent applications, e.g.: coding agents, assistant CLIs and multi-agent tools.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

Turn your Claude Pro/Max subscription into an OpenAI-compatible API for your IDEs and devices — LAN auth, per-key quotas, response cache, disciplined cli.js alignment. $0 extra cost.

Agent wallet, credential vault, and governance layer for autonomous AI agents

키움증권 REST API CLI — 주식 시세·계좌·주문·자동매매·미국주식을 터미널에서 (Kiwoom Securities CLI for Korean & US stocks)

A security-first bridge between Claude Code (MCP) and Chrome — HMAC pairing, domain allowlist, per-domain evaluate opt-in.

A local-first control layer for AI agents

Sandbox runtime for AI coding agents. Firecracker microVMs, a single Go binary, snapshot/fork as first-class primitives.

Signal for AI assistants: an MCP server + CLI with searchable local message history, groups, polls, @mentions and 80+ tools on top of signal-cli. 100% local, read-only mode available.

Runnable examples for gopact

Official extensions for gopact

Multi-agent terminal heatmap, token FinOps, workload replay, and verifiable receipts for 15+ agents

Fast, compiled CLI for inspecting Rails projects

Platform-agnostic work-orchestration for AI coding agents — one pane of glass (issues, scm, ci, deploy, notify) across providers, via MCP + CLI.

Your durable workspace across AI agents.

AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.

Bitemporal memory for AI agents: deterministic contradiction resolution, provenance, and retrieval at any point in time.

Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬

Plan ? execute ? verify workflow automation for AI coding agents. One installer, five runtimes: Claude Code, Codex, Gemini CLI, OpenCode, Copilot.

A universal git-native AI agent framework. Your agent lives inside a git repo — identity, rules, memory, tools, and skills are all version-controlled files.

Agentic First OpenAPI & AsyncAPI Documentation. Works 100% offline, straight from disk, shareable or publisable to any static host. AI and agent output built in, Built in API Catalog generation.

AI Olympus — an agentic AI framework for building and maintaining Laravel web applications: Claude Code subagents, coding-standard rules and agent skills

Local multilingual code graph for impact analysis — typed edges, incremental indexing, CLI, MCP, and an embeddable Go API.

AI vision GUI automation for browsers, mobile apps, desktops, and games — no DOM, no selectors. Standalone or on top of Playwright / Selenium / Appium / pytest.

Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20-40% tokens via RTK compression, auto-fallback from subscription to cheap to free providers, multi-account round-robin, and a local dashboard.