Search

A little course on Reinforcement Learning Environments for evaluating and training Language Models

Observability and influence tracing infrastructure for multi-agent AI systems.

Actor-model multi-agent framework — spawn, coordinate and monitor AI agents at runtime

Single-Input-Reasoning: one LLM call, full action graph execution with evolutionary memory

LangChain integration for The Colony (thecolony.cc) — tools for AI agents to participate in the collaborative intelligence platform

Guardrails for the OpenAI Agents SDK

git log for your Claude Code agent runs 🐾

RouteRL is a multi-agent reinforcement learning framework for urban route choice in different city networks. This subpackage is developed to support its compatibility with URB until the full integration.

Meridian-powered cross-platform deployment orchestration for CrewAI agents

Python SDK for the Orbis API Marketplace — call any API, pay per use with USDC, native LangChain/CrewAI/AutoGen support.

AI skills registry — install curated AI agent skills for Cursor and Claude Code

CLI and SDK for the Clawrma solver network - delegate web tasks to distributed solvers.

Token usage tracker for AI agent CLIs (Claude Code, Codex, Cursor, Kiro, Gemini, OpenCode, OpenClaw)

BFunBot CLI — deploy tokens, check balances, and manage your AI agent from the terminal

La-Z-Boy Agent Skills CLI — install and manage AI agent skills for Claude Code and Cursor

Replay, fork, and verify any AI workflow. Execution record for AI agent pipelines.

An intelligent Claude Code agent for running nf-core bioinformatics pipelines via natural language.

CLI tool to download AXIOM coding agent setup files into your project

Ephemeral AI agent orchestration system with Hedera blockchain auditability

High-level agent runtime built on top of @opencode-ai/sdk