#ai-agent

Link compounds to protein targets, rank bioactivity (IC50/Ki/EC50), and look up drug mechanisms and indications over ChEMBL via MCP. STDIO or Streamable HTTP.

⚡ High-performance job queue for Bun. SQLite by default, PostgreSQL multi-broker when you scale. DLQ, cron, SQLite S3 backups, and native MCP. No Redis.

Plans new work as Flyto2 workflows, then reuses exact solved procedures without another planning call.

MCP server for Azure Data Explorer (Kusto), enabling AI agents to explore, query, and understand telemetry using KQL.

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

Nimbus Agent — SDK (@nimbus-dev/sdk). MIT, dependency-free TypeScript contract for authoring Nimbus MCP connectors & extensions.

Agentic Spec-Driven Development — 13 agents, 58 MCP tools, 10-phase enforced pipeline. From meeting transcript to PR in one command. Install via npm install -g specky-sdd@latest

The AI agent that physically operates a phone — the way you do.

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

TapTap 小游戏开放能力 mcp

A Go framework for chat-network agents: an IRC bouncer, browser UI, and bot orchestrator in one static binary, with an optional LLM hookup for AI features. Stewarded by xShellz.

🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

The lightweight framework for building agents

Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

Persistent memory MCP for AI agents — SQLite, knowledge graph, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations

AI-native Lexical rich text editor. Edit, render, SSR, and AI agent protocol (LiteXML) — all from one schema. React 19, TypeScript, Vanilla Extract, ESM.

Open-source AI pentest and compliance-readiness CLI by NullSquare.

A runtime for reliable multi-agent systems with durable workflows, resumable execution, and human-in-the-loop control

该仓库未发布描述。

Provenance layer for AI agent sessions — record, replay, and reason about Claude Code (and other agent) work.

Personal AI assistant as a single Go binary — self-hosted, no Python or venv, curl to running in under a minute. CLI + Telegram, any LLM provider, long-term memory, skills, cron.

Access FEC campaign finance data through MCP. Query data about candidates, money trails, and election filings. STDIO & Streamable HTTP.

Search UniProtKB by protein function, fetch curated records, map IDs across databases, and pull reference proteomes, taxonomy, and sequences via MCP. STDIO or Streamable HTTP.

A CLI for AI agents to operate GitLab — repos, issues, merge requests, pipelines, and more. Structured output and composable commands, built for LLM tool use.

面向 AI Agent 的微信公众号创作与发布 CLI：Markdown 排版、AI 配图、预览与草稿创建；支持由浏览器 Agent 保存知乎、CSDN、头条未发布草稿。

A governance harness for AI coding.

Ship fast. Ship right. Ship everything. Ship accountably. AI-powered dev system: slash commands orchestrate specialist agents from idea to hardened production. Imports godplans plans and godaudits reports; artifacts as .mdx.

天枢harness是一个的终端编程智能体，它要回答的核心问题是：模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环，不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境（CVM），把目标、状态、证据、资源、权限与终止条件从对话历史中外部化，由运行时持续管理。同时对deepseek v4极度优化。

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use