Havuz

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Agent-native Stata CLI for AI coding agents (Codex, Claude Code, Cursor). Run .do files, inspect data, and return econometric results as JSO

Open communication and task handoffs for AI agents — self-hosted email, task threads, approvals, and webhooks over MCP and REST. Apache-2.0.

把微信公众号文章下载为多种格式并在应用内浏览;支持直接订阅公众号，每日自动更新公众号文章至本地,同时提供CLI 供 AI agent 调用。

Independent, source-attributed Hermes Agent workflows, skills and community projects. A static archive with public metrics and owner-reviewe

Turn any MCP server into a CLI in one command.

Drive a real browser from the command line and from MCP. Stable element refs, zero dependencies.

Hermes Agent plugin & skill for Twitter search, monitoring, follower exports & X actions. Not affiliated with X Corp.

An open-source runtime that lets your AI agent operate your machines.

248 small Jev decisions for JavaScript and TypeScript: route, rerank, gate, grade, compare, and label text for agents, RAG, support, code re

Production-ready MCP server for Apache DolphinScheduler (小海豚) — lets AI agents build, schedule, run and recover workflows

Lightweight file host and upload tools for coding agents to add artifacts to pull requests. Add CI checks for screenshots. Cloud and self-ho

Agent-native task management for humans and AI agents, built around a local-first API, SQLite storage, projects, calendar views, backups, an

Agentizable: an open-source bounty network where AI agents post, fund, claim, solve, verify, and get paid for digital work.

Safe MCP server for Plastic SCM / Unity Version Control (cm 10.0.16.6656+, UVCS 11.x). Readonly by default; guarded write tools.

Search your Claude Code conversation history by content (not just titles), then resume any session. grep + fzf, no index.

aside-codemode, Aside içindeki JavaScript REPL üzerinden dosya araması ve browser işlerini tek çağrıda çalıştırıp modele yalnızca seçilmiş sonuçları döndürür.

Neden yükseliyor · 14 günlük yaşına karşılık 124 yıldız ve son 28 günde 287 commit görünmesi, hızlı bir başlangıç ve yoğun geliştirme faaliyetine işaret ediyor. README'deki ölçülebilir arama ve browser örnekleri de ilgiyi artırabilir; ancak yükselişin kesin nedeni bilinmiyor. Commit'lerin yalnızca 2 farklı yazardan gelmesi, faaliyetin geniş katılımla desteklendiğini göstermiyor.

Experimental scenario analysis for real-life events forecasting with Codex or Claude

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

Durable MCP control plane for long-running Codex Desktop tasks

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it,

Headless verification browser for AI coding agents: 35 ms one-call checks, pixel diffs, live human hand-off

Web tasks that compile. Other browser tools tell your AI agent the click worked. chrome-agent reads the page back after every action and ans

The runtime reliability layer for AI agents.

Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

oo is OOMOL's CLI toolkit. Everything can be done in the CLI.

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

Multi-account Google Workspace (Gmail, Drive, Calendar, Sheets, Docs) + Slack MCP servers for Claude Code. Setup guide with CLAUDE.md for AI

A self-hosted AI agent runtime with WebUI, MCP tools, context governance, and Record & Replay for deterministic execution & evaluation.

Index, search, summarize, and approval-gate local Codex sessions through OpenClaw/MCP. Agent-first recall and dry-run orchestration for Code

让 Agent 操控 Windows 桌面软件

Verified catalog of 300+ APIs and MCP servers with opinions and statistics so that AI agents can call after a one-time API key/OAuth setup.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST AP

Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime for agent-composable dashboards — layout-as-data, o

Go library, CLI, and MCP server for Camoufox browser automation.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Gaia is a living, open registry of every AI agent skill — structured as a leveling skill graph. Live site: https://gaiaskilltree.com/

Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.

Compile an API, an MCP server, a database or a web page into a CLI your agent can run. Ten engines, one output contract, 4.1x less context t

Let your coding agent develop firmware on the real board, with the hardware as the gate.

The knowledge graph for APIs your agent can trust. Maps any API — even messy, paywalled, or on-chain ones — into a verified graph your agent

Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.

Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref

Structured file edits for AI agents (JSON/YAML/TOML, markdown, AST, dry-run, MCP). Not a generic filesystem MCP.

Hermes Doctor для диагностики и approval-gated repair planning в Hermes Agent.

Local-first, single-binary router for discovering and loading large agent skill libraries without flooding the model context.