Explore

Dynamic agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS spaced repetition and memory consolidation. Zero-dependency TypeScript library,

Node.js·Apache-2.0·★ 27·No key

VDA5050-compatible cloud service for fleet mission dispatch

Skill·Apache-2.0·★ 106·No key

The agent-native runtime where a typed, declarative stitch replaces fetch — for humans and agents alike.

Node.js·Apache-2.0·★ 20·No key

A short-term planning system for engineering teams — keep engineers focused, run daily sprints, and track unplanned work. Built on GitHub Projects v2 (no database of its own): one Go binary with an em

Go·Apache-2.0·★ 34·No key

Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.

Python·Apache-2.0·★ 16·No key

Type-aware, secret-safe clipboard history for Claude via MCP. Rust binary, macOS + Linux. Ships as .mcpb.

Skill·MIT·★ 19·No key

Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a

Python·AGPL-3.0·★ 4·Few stars·No key

Provide full Python API access to NotebookLM features, including advanced functions beyond the web interface, via CLI and AI agent integration.

Skill·MIT·★ 3·Few stars·No key

Executable architecture governance. A CLI, MCP server and REST API that check a repository against Rego/OPA rules — and report a rule they could not evaluate as a failure, never a silent pass.

Node.js·MIT·★ 2·Few stars·No key

Your Gemini web app as a service — turn the free Gemini web interface into a programmable HTTP API for image and video generation

Skill·MIT·★ 6·No key

Definitive MCP server for Ableton Live — full LOM coverage, embedded device knowledge base, and declarative music recipes. Build real music in Live from plain language with Claude, Cursor or Codex.

Node.js·MIT·★ 9·No key

A runnable Docker Compose lab demonstrating the three structural failures of observe-and-detect agent governance. No API keys, no cloud accounts, 60 seconds to run.

Skill·Apache-2.0·★ 9·No key

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

Node.js·MIT·★ 3·Few stars·No key

How much water and energy does AI use? MCP server and JSON API for the water and energy footprint of AI, with boundary, assumptions and sources attached.

Hosted by author·MIT·★ 1·Few stars·No key

A deterministic verification engine for agents. Fires the edge cases your sandbox never sends — duplicate webhooks, declined cards, rate limits — then proves a fix: the same scenario fails on the old

Node.js·MIT·★ 1·Few stars·No key

Pre-trade safety check for Solana AI agents — cabal/coordination, honeypot and serial-launcher deployer history in one MCP call, with the transactions behind every wallet cluster. 5 free scans/month,

Hosted by author·MIT·★ 1·Few stars·No key

Run non-urgent LLM tasks at the cleanest grid hour before a deadline. MCP server + TS/Python library. Apache-2.0.

Node.js·Apache-2.0·★ 1·Few stars·No key

bouncer — static compliance-controls checker (UK Online Safety Act & ICO Children's Code) as deterministic rule packs. CLI + MCP. No LLM.

Node.js·MIT·★ 1·Few stars·No key

MCP server that helps AI agents pick the lowest-carbon cloud region for a workload.

Node.js·MIT·★ 1·Few stars·No key

MCP server for the Cookin API: Solana and Pump.fun token intelligence, paid per call in USDC over x402 or with a Cookin Pro key.

Node.js·MIT·Few stars·No key

Delivery gates for AI coding agents, because green tests are not proof. Breaks your code on purpose and reports the breaks no test noticed. Runs a change's new tests against the code from before it. I

Node.js·Apache-2.0·Few stars·No key

MBTA MCP — Boston real-time transit via the MBTA v3 API (api-v3.mbta.com)

Hosted by author·MIT·Few stars·No key