
Open-source SDK for building MCP apps and servers, with a hosted cloud for them
- Freemium
- Agent framework
- 11K GitHub stars
- Developer tools

Open-source SDK for building MCP apps and servers, with a hosted cloud for them

Strands toolkit with a ready agent harness, sandbox and evals in Python and TypeScript

Google's open-source Go toolkit for building and deploying AI agents

Claude Code-style full-screen terminal interface for DeepSeek Harness

Learns from past agent sessions to cut coding-agent token costs

Self-evolving engine that lets agents share and reuse learned capabilities

Python framework for building autonomous and traditional AI agents

Use ChatGPT on the web to plan and review while Codex executes your coding tasks

Microsoft toolkit for policy enforcement, identity and audit of autonomous agents
Local-first MCP server for messaging and shared work-state between coding agents
Runs locally
Local code search for coding agents that returns only the relevant snippets

Self-hosted registry for publishing, finding and governing agent skills

Open-source Python framework for building and orchestrating multi-agent AI systems

Open-source terminal agent that runs on your machine with any model

Open-source SRE agent that investigates production incidents and finds root causes

Continuity layer that keeps one unit of work moving across different agents

MCP platform with SDKs, desktop IDE and managed hosting for MCP servers

Open-source CI runners and microVM sandboxes billed by runtime

TypeScript SDK implementing Hashgraph Consensus Standards from HOL

Autonomous web testing agent that checks functionality, performance, UX and security
Serves the MDMA spec, authoring prompts and docs to AI assistants
Runs locallyOffline review that flags agent changes which weaken tests, assertions or CI
Runs locallyZero-log MCP server with 49 tools for AI guardrails, secret scanning and EU compliance
qBittorrent MCP server that diagnoses uploads and manages many instances
Runs locallyProduction-aware review of changes against your AWS or Google Cloud setup, via MCP
Verify and explain signed proof-of-delivery receipts for x402-paid APIs
Color tools for AI agents: contrast fixes, Material 3 themes, palettes and CSS matching
Runs locallyWrite, check and dry-run Lugh agent programs with policy, budgets and approvals
Runs locallyShared tasks, decisions, skills and tools for a team's coding agents
Not checked yetMessaging and advisory locks so several Claude Code sessions can share one repository
Runs locally