Context7
upstash/context7
Up-to-date code docs for every LLM and IDE.
Context7 is an MCP server that injects up-to-date, version-specific library docs into an agent's context on demand — killing the stale-training-data hallucinations that plague codegen. One of the most-installed tool layers in modern harnesses.
In the news
Best of Agent Harnesses tracks 167 harnesses — and their graveyard
The Best of Agent Harnesses list ranks 167 agent harnesses weekly by capability, autonomy and recovery, ships an MCP server so agents can pick their own harness, and maintains a graveyard that flagged a 268k-star repo for suspected star manipulation. Curation itself becomes harness infrastructure.
Anthropic moves MCP toward open foundation governance
Anthropic announces plans to donate MCP to a neutral foundation, with new registry, auth and sandbox specs — cementing MCP as vendor-neutral infrastructure for the entire agent ecosystem.
Anthropic introduces the Model Context Protocol
Anthropic open-sources MCP, a standard for connecting AI assistants to data and tools. Within a year it was adopted by OpenAI, Google, Microsoft and most of the agent ecosystem — becoming the de-facto tool-connect layer of agent harnesses.
Related projects
OpenClaw
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
OpenClaw (born as Clawdbot in late 2025) is a self-hosted personal agent that connects your chats, email, browser and terminal into one always-on assistant. Its explosive growth — hundreds of thousands of stars within months — made 'personal agent harness' a mainstream category.
superpowers
obra/superpowers
An agentic skills framework and software methodology that works.
superpowers is the most-adopted skills pack in harness engineering: skills, instincts, memory, security and research-first workflows for Claude Code and 13 other harnesses (Codex, Cursor, opencode, Gemini CLI and more). Treats harness engineering itself as the discipline.
Firecrawl
firecrawl/firecrawl
Turn websites into clean markdown for LLMs and agents.
Firecrawl crawls, scrapes and converts entire sites into LLM-ready markdown with structure — the go-to ingestion primitive for agent context pipelines.