1241 packages found
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflo
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools,
Open geographic query engine — ask place-based questions in natural language, get answers on a map. Covers disasters, de
Nino Agent 是一个 API-first、多语言可演进的 Agent Harness 项目。当前可执行版本使用 Python 3.12，提供通用 Orchestrator、受控 Specialist ReAct Worker、共享
Open-source 3D AI agent framework — GLB/glTF avatars with LLM brains, memory, emotions, and autonomous payments. MCP ser
Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Agent-native Node.js CLI + MCP runtime for generating, validating, and packaging handoff-ready full-stack web projects.
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools,
Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Olla
A lightweight, zero-footprint TypeScript MCP server that lets AI assistants interact with the Godot 4.x game engine.
AI runtime for creating, running, and supervising background AI workers.
Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and se
GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools: scene management, GDScript LSP, DAP debugger, sc
CI for ink stories — compile checks, exhaustive branch playtesting, dead-content detection. MCP server + CLI.
The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
Local AI operations console for supervised agent work.
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work.
Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-na
Harness-oriented agent system framework for production-grade LLM agent applications
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integratin
Deploy an MCP server with MCP Apps (interactive HTML widgets) on Amazon Bedrock AgentCore Runtime, connected to AI hosts
Your super agent for work: local-first, learn your working context in mins and never forget it.
@hjqcanLocal-first, auditable memory layer for AI apps and coding agents — Codex, Claude Code, MCP, HTTP, TypeScript, and Pytho
MCP server for progressive brand governance — extract, compile, and audit brand identity systems
ContextLattice is the local-first control plane for long-horizon agent memory and coordination.
Local visual debugger for AI agent runs: replay failures, inspect prompts/tools/results, and export redacted evidence.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
MCP Server for IBM Decision Intelligence to extend AI experience with decisioning capabilities
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Rust MCP server for multi-agent coordination: 34 tools, Git-backed archive, SQLite indexing, advisory file locks, and an
Action Control for autonomous agents. Check posture. Gate risky actions. Prove execution. Fits your existing agent stack
Local MCP broker that exposes one compact MCP entry for MCP clients while routing to many configured upstream servers.
MCPMate is a progressive MCP management center for organizing servers, clients, profiles, capabilities, and runtime visi
Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a d
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
Sandboxed bash for agents. Track changes on every command.
AI supply-chain security scanner and self-hosted control plane for agents, MCP, SBOM/SARIF, graph findings, runtime enfo
The agent-native runtime where a typed, declarative stitch replaces fetch — for humans and agents alike.
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks,
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their e
Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency
Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shad
Embedded agent runtime compliance layer — WASM sandbox, MCP firewall, capability manifests, verifiable rollouts, and tra
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit
Triptych OS (Agent OS) integrations for deployed agents: execute-first tools, Micro ECF exports, x402 calls, receipts, a