Search

Self-hostable AI agent platform with visual Studio. Pydantic AI, native RAG (Pinecone), MCP, multi-step workflows.

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.

Self-hosted AI agent with epistemic integrity — fact-labeled, source-cited, verifiable. Run it yourself.

A Bun + FastAPI monorepo for running a mobile-friendly AI workspace in the browser, backed by a configurable LLM gateway and repository indexing APIs.

The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"

Hyperlight CodeAct integrations for Microsoft Agent Framework.

MVAR: Information Flow Control for LLM Agent Runtimes

Foundry Hosting integration for Microsoft Agent Framework.

CLI-first memory engine for LLM applications.

LangChain integration for TrustRAG — trust-verified retrieval + LangGraph multi-hop agent with trust budget

Framework-agnostic payer for the x402 HTTP payment protocol. Works with LangChain, CrewAI, AutoGen, LangGraph, or any other agent framework.

Lean Swarm multi-agent prediction and simulation engine

Shared LLM proxy helpers for MeshAgent

CRAP metric CLI for TypeScript: combines cyclomatic complexity and test coverage to find risky code, with a bundled cross-agent AI skill.

Jira CLI — kubectl for Jira, designed for AI agents and automation

CLI toolkit for turning OpenAPI specs into agent-ready skills, typed client schemas, request validators, endpoint tests, and exploration tools.

Skill management and scheduling toolkit for AI Agent frameworks

Crash-test AI agents before they ship. Drives a coding agent (Claude or Pi) to generate adversarially-validated benchmark worlds. Ships `quaver agent generate`, `quaver lint`, `quaver validate`.

The official Node.js SDK for [Sensu](https://sensu-ai.com) — observability for AI agents.

Curve Agent SDK