Search

External ROS-node skill: frontier exploration and safe wandering via agenticros_explore + Nav2.

Next.js and Python AI agent starter with tools, streaming, structured output, and jobs.

A process-quality benchmark for LLM agents: it grades how an agent worked, not whether it passed — and every LLM-as-a-judge sits a calibrated exam before it may score.

Model provider adapters for Toren (Anthropic, OpenAI) — each SDK loads lazily on first use.

Velocity AI Engine — Universal AI Agent Orchestrator with Formal Verification

Tencent Cloud Service CLS observability plugin for DeepSeek Harness — direct upload to Tencent Cloud CLS

Gecko Agent — autonomous agents connected to the Gecko network.

DEPRECATED: Deployment tooling for Deep Agents. Use Managed Deep Agents (`uv tool install managed-deepagents`, `mda`) instead: https://docs.langchain.com/langsmith/python/managed-deep-agents-overview

Defensive LLM agent honeypot & token tarpit - FastAPI backend with an OpenAI-compatible endpoint that wastes hostile agents' context windows.

LlamaIndex reader and tools for the Web Metadata, OpenGraph & Contact Extractor API — ingest any URL as a clean-Markdown Document for RAG, plus agent tools for contacts, tech stack, and SEO auditing.

JSON Schema definitions and TypeScript types for VAT agent manifest format

SQLite-backed projection store for VAT, on Node's built-in node:sqlite

The sleep cycle for AI memory: every memory carries its evidence; a scheduled pass keeps the evidence honest.

Provider-neutral lifecycle control layer that helps coding agents plan, execute, validate, and prove software tasks to completion.

Factory for building LangChain deepagents equipped with episodic, semantic, and procedural memory.

The god agent for solopreneurs on Mac. Opens terminal sessions it can undo, runs agent swarms, builds iOS apps, and writes its own next version for you to approve. 39 features, 79 tools, MIT, your key or a local model.

Pi extension wrapping the GitHub gh CLI as a single typed tool.

Open-source financial research agent whose false-positive rate is measured, not assumed. Permutation tests, multiple-testing correction, and a published calibration study that found (and fixed) a 45% false-positive rate.

Zero-infrastructure in-memory RAG prototyping framework for Python.

Wytness — the blackbox recorder for AI agents. Customer-held PII keys, per-event Ed25519 envelope, audit-ready evidence packs. Built on Microsoft's Agent Governance Toolkit.