Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Local-first MCP server that gives AI coding agents repo and org memory from GitHub PR history, code, tests, regressions, architecture, and cross-repo impact.
SkillMIT★ 1Few starsNo key
ANCHOR is an agentic workspace for ingesting technical PDFs, extracting grounded knowledge, and connecting evidence to collaborative engineering canvases.
PythonMIT★ 4Few starsNo key
AI code generator for Solana Anchor programs — TypeScript clients, Rust accounts, tests & full programs from your IDL. MCP server + CLI.
Node.jsMIT★ 2Few starsNo key
Source-grounded chunk validation as a primitive. Spring Boot service exposing two interfaces (LLM-to-LLM and human-facing) over the same hierarchical document model.
SkillApache-2.0★ 2Few starsNo key
MCP server exposing 14 anchor-x402 services as agent tools. Pay-per-call USDC via x402 on Base mainnet. Works with Claude Desktop / Claude Code / Cursor / any MCP client.
Node.jsMIT★ 1Few starsNeeds a key
Context engineering toolkit for AI applications. Token-aware pipelines, hybrid retrieval and provider-agnostic formatting.
PythonMIT★ 4Few starsNo key
Watches AI coding agents, records every edit with the prompt that caused it, and tells you which attempt actually worked — decided by your test suite. Local only.
SkillMIT★ 1Few starsNo key
The memory layer for your AI agents — remote MCP server with semantic memory, agent keys, and a web dashboard
SkillMIT★ 2Few starsNo key
PythonMIT★ 2Few starsNo key
SkillMIT★ 4Few starsNo key
Hosted MCP server for identity resolution and write guardrails for AI agents. Read-only proxy to the Anchord API.
Node.jsMITFew starsNo key
SkillMIT★ 2Few starsNo key
Never lose critical data in Claude Code. Extracts only nouns and verbs from conversations — 93% compression vs 70% for summaries. Structured anchors with bidirectional links, auto-saved via hooks.
SkillMIT★ 5No key
Agent-native CRM as 25 MCP tools. Enrichment waterfall (Apollo → Hunter → AI), shared cache, per-call audit. Powers https://anchorr.app — connect at https://anchorr-mcp.mgthompo.workers.dev/mcp
MCPLink only★ 1Few stars
An interactive Claude Code skill for planning Solana Programs using Anchor
SkillLink onlyFew stars
Cooperative open research where every step is auditable. Multi-scale claim graphs around causes that matter.
SkillAGPL-3.0★ 4Few starsNo key
Anchor coordination methodology (four-role multi-agent framework). The architectural-invariant gate it spawned is now its own tool → github.com/johnpatrickwarren-oss/sprag
SkillApache-2.0★ 1Few starsNo key
Give AI coding agents an instant head start in every session with persistent project memory, AST-based code maps, and automatically synchronized repository context.
Node.jsApache-2.0★ 4Few starsNo key
Asynchronous, anchored AI edits for VS Code through MCP
SkillMITFew starsNo key
The human-in-the-loop reviewer for agentic coding. Agent it. Review it. Feed it back.
SkillApache-2.0★ 9No key
Coding Agent skill for scaffolding Solana Anchor projects, recovering missing Anchor CLI setup, and generating comprehensive runnable tests for Anchor programs.
SkillMITFew starsNo key
SkillMIT★ 3Few starsNo key
Who stands behind it
