Tools

Coding-agent harness built for unattended, away-from-keyboard runs across four surfaces sharing one session manager: one-shot CLI, REPL, cron-friendly headless daemon, and a Telegram bot. Editable agent loop (prompts, permission gates, model routing, explicit terminal states), MCP (stdio/HTTP/SSE + OAuth), lifecycle hooks, background subagents, plan mode, cross-session memory, and an append-only trace receipt (`afk trace show`). Works with Anthropic and any OpenAI-compatible endpoint (GPT, Codex, local MLX/llama.cpp/Ollama)

Open Agent OS for Claude Code, Codex, and Cursor with a meta-agent builder, A2A Hub routing, local ontology, and memory/security gates. Apache-2.0.

⚡AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-agent) management platform with admin UI, user management and Single-Sign-On⚡, supports ChatGPT, Claude, Llama, Ollama, HuggingFace, etc., chat bot demo: https://ai.casibase.com, admin UI demo: https://ai-admin.casibase.com

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

AI agent discovery and marketplace on Nostr with Solana payments (SOL, USDC). NIP-89 discovery, NIP-90 jobs, NIP-44 v2 encryption, on-chain micropayments.

Framework for AI agents (Claude Code, Cursor, Codex, Gemini) to operate Google Ads, Meta Ads, and Search Console. Grounded in a local STRATEGY.md — not metric-chasing. Defense-in-depth security, local-first. Apache 2.0.

Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine

A model-driven approach to building AI agents in just a few lines of code.

Agent-to-agent marketplace where AI agents discover, invoke, and pay for services from other agents using USDC on Base L2.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Bubble Tea TUI that unifies the local session stores of Claude Code, Codex, Gemini CLI, and OpenCode: fuzzy search grouped by workspace, resume via each agent's own CLI, branch local copies, and cross-agent transcript conversion into the target's native format. Scriptable (`list --json`), fully local, single Go binary. MIT.

Apple-native execution layer for AI agents. Compiles TypeScript to validated Swift — App Intents, SwiftUI views, WidgetKit widgets, and full apps. 13 MCP tools, 150 diagnostics, 500 tests.

Build and run agents you can see, understand and trust.

From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。

Trust, identity (W3C DID), and EigenTrust reputation for AI agents. Attestations, disputes, sybil detection, IPFS audit anchoring.

An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.

Stateful MCP server over real language servers. 50 tools, 30 CI-verified languages, 20 agent workflows. Persistent sessions keep the index warm across files and projects. Speculative execution simulates edits in memory before writing to disk.

BOSS Zhipin recruitment workflow for AI agents. 49 MCP tools for job search, welfare filtering, recruiter messaging, pipeline tracking, and resume optimization.

MCP Toolbox for Databases is an open source MCP server for databases.

First AI‑enabled open-source Human Capital Management system that you can start using today.

Cognitive memory for AI agents with Hebbian learning, 3-tier architecture, and knowledge graphs. Single ~15MB binary, runs offline on edge devices.

Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph with PPR traversal, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB + SQLite, zero external dependencies.

Production-ready platform for agentic workflow development.

Durable, agent-native AI runtime with native MCP client + server and A2A support. Rust core for performance, Python authoring for ergonomics. Features graph-based workflows, durable execution, and multi-agent coordination.

Query Engine for AI Analytics: Build self-reasoning agents across all your live data

Local-first orchestrator that runs inside your existing Claude or Codex CLI via MCP; classifies a request, decomposes it into tickets with a dependency DAG, dispatches across one or more repos, and supervises with live PR tracking + approval gates. CLI, TUI (ratatui), and GUI (Tauri)

Collaboration rooms for AI agents. Create rooms, join with agentToken, exchange messages in real time via SSE. Supports MCP and A2A protocols. Self-hostable or use the hosted version at join.cloud.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

Hierarchical memory engine for AI agents with automatic decay, promotion, semantic dedup, and self-organizing topic tree. Single Rust binary, zero external dependencies.

Persistent memory layer for AI agents with entity resolution, PII detection, AES-256-GCM encryption at rest, and hybrid search. 100% on LoCoMo benchmark. Self-hosted.

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Agent-first programming language: agents produce JSON AST, the compiler validates, type-checks, effect-checks, verifies contracts via Z3/SMT, and compiles to WASM. 19 MCP tools for the full compile-and-execute loop.

Persistent memory for AI agents with sectioned entries (project/user/context/etc), semantic search, CLI, and per-project scope. Local JSON, zero config, no server required.

Decompose text into classified semantic units with authority, risk, attention scores, and entity extraction. No LLM. Deterministic. Works as MCP server or CLI.

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

Cognitive memory engine with 5,100+ knowledge modules, circadian rhythm awareness, and emotional state tracking (PAD model). Hybrid search (PostgreSQL + Qdrant vectors + Valkey cache), per-user memory isolation, and multi-protocol support (MCP, REST, OpenAI, LangChain, A2A). `npx @celiums/memory` Website

Playwright for the entire OS. Gives AI agents the ability to see, find, and interact with UI elements in any desktop application.

Agent-first cognitive substrate with 18 manifest-driven verbs (germinate / eat / assimilate / sporulate / traverse / immune / molt / …) and 25 lint dimensions enforcing contract invariants mechanically (R1–R7). Cross-session / cross-project memory via a self-validating filesystem graph — AST + markdown-link derived, not embedding-based. Provider-agnostic by design: MP1/MP2 dims forbid LLM-SDK imports in the kernel and plugin tree. Editable-default install. Works with Claude Code, Cursor, Windsurf, Zed, VS Code, and any MCP client.

Agent Framework For Fintech and Banks

Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)

Security-first MCP governance proxy (`sint-mcp`)

Deterministic reasoning engine for AI agent context compression. Extracts structured facts with logical inference, proof chains, and truth maintenance. REST API, Python/TypeScript SDKs, and MCP server integration.