Search

Context-efficient project search and bounded code analysis for Pi and remote MCP clients, powered by ripgrep with stable cursors, source inspection, and structural evidence.

Rust multi-agent coordination platform: HTTP/SSE gateway, agent runtime with token-budgeted context, per-tool sandboxing, multi-provider LLM support.

Document-grounded adaptive tutoring with bounded tool-use agents

Unified Atlan Agent Gateway management and tracing SDK

A modular agent framework for learning and research

Local-first evaluation framework for RAG pipelines and AI agents

DoStuff - AI agent harness with global CLI, pipx install, and persistent session storage

Catch LLM agents that fail silently — no ground truth required.

The verifying analysis runtime for elbi: an LLM loop that cannot report an effect it has not verified.

Agente opencode + base RAG com documentacao fiscal eletronica oficial brasileira (NF-e, NFC-e, CT-e, MDF-e, SPED) distribuido como pacote npm.

Ultra-fast local agent shell for Windows.

Based on Agentation by Scott Sunarto; adds bb mentions, queued delivery, and verified identity tags to visual feedback.

agent包，目前有message，prompts模块，最近一次更新是26-8-27

Web frontend for Flowwit — a chat interface and visual workflow editor for a multi-agent LLM platform.

Robust and efficient coverage paths for autonomous agricultural vehicles. A modular and extensible Coverage Path Planning library

Peer review for AI agents using independent model juries and deterministic aggregation.

Build durable agent harnesses so smaller models can do repeatable, verifiable work — a versioned folder with tools, guardrails, validators, and measured evidence from every run.

Autonomous self-learning AI agent architecture exploring reinforcement learning, memory persistence, dynamic planning, and tool use.

Python SDK from Google for agents, structured generation, and observable LLM apps

AgentK effect-integrity layer for AI agent tool calls.