v1.0.0 · Apache-2.0
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
v0.3.7 · Apache-2.0
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
v2.8.3 · MIT
专门为 agent 打造的 agent 搜索工具,具备多语言搜索能力,覆盖中文/英文/学术/代码/购物/金融/新闻/百科。
v0.8.25 · MIT
BioMCP: Biomedical Model Context Protocol
v3.0.0 · MIT
Helping coding agents never make mistakes working with public or private libraries without wasting the context window.
— · Apache-2.0
An open-source AI agent that brings the power of Gemini directly into your terminal.
v0.0.1 · Apache-2.0
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
v5.7.0 · MIT
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
v2.31.1 · Apache-2.0
AI said it finished. Flyto2 shows the proof.
v0.4.0 · no license
Next.js Development for Coding Agent
v0.0.1 · MIT
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
v0.2.5 · Apache-2.0
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness.
v0.20.3 · MIT
Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.
— · MIT
🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.
v1.3.2 · MIT
Odoo MCP for AI agents — gated writes, multi-instance. Hosted product: https://erpipe.com
— · MIT
Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results
v0.6.82 · MIT
Local-first coding agent memory for Claude Code and OpenAI Codex
v0.25.1 · no license
嘉立创EDA专业版(EasyEDA Pro)自动化:给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作,CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱,以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.
v0.8.0 · MIT
The open-source context layer for your AI. Catalog your tables, topics, queues and APIs then expose real metadata to your AI agents.
v0.9.36 · MIT
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
v1.99.421 · Apache-2.0
Unified npm bootstrap for the Yaver agent, SDK injection, and local-first developer runtime
v2.16.3 · MIT
Safari browser automation for AI agents — native macOS, zero Chrome overhead. 97 tools via AppleScript + JavaScript.
v1.4.4 · MIT
Persistent memory for agents. Corrections stick, context compounds, every session starts smarter.
v0.3.7 · Apache-2.0
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.