Search

Multi-agent system for HED annotation generation and validation

Unified AI reliability platform. One install, 12 diagnostic engines. Continuous monitoring, fault diagnosis, and compliance for LLM pipelines.

File storage and sandbox backends for AI agents

A CLI tool to inspect, diagnose, and manage local ports and processes with predictable output for humans and AI agents.

LangGraph-based multi-agent KV-cache communication protocol for LLMs

Local Codex-to-Claude bridge CLI

The OpenTelemetry for AI agents — structured traces, semantic diffs, and failure pattern mining

A library for multi-agent systems evaluation and benchmarking.

Lint, score, and optimize AI agent configuration files (CLAUDE.md, AGENTS.md, Cursor rules)

Coordination mesh for multi-agent orchestration

Coordination mesh for multi-agent orchestration

Budget-Aware Agentic Routing — route LLM calls intelligently between cheap and powerful models with a hard budget cap.

Real-time pixel-art dashboard for multi-agent systems. Production observability meets engaging visualization.

Git-native, Merkle-rooted multi-agent shared memory with GraphRAG

SUBSTRATE cognitive memory provider for Microsoft AutoGen agents

AgenCLI: a multi-agent terminal workspace built in Python.

Self-Improving Agentic RAG Engine - Evolve multi-agent RAG pipelines using Quality-Diversity optimization

A Dual-State Agent Framework for reliable LLM code generation with guard-validated loops

Automatically optimize agent skills using Gemini and ADK

StreetRace is an agentic AI coding partner designed to help engineers leverage AI capabilities directly from the command line to create software.