Search

Governance middleware for LangChain 1.0 agents — powered by axor-core compression engines

Runtime monitor for LLM agent interaction protocols based on session type theory

tmux for AI Agents — Orchestrate multiple AI coding agents in parallel with one command

Self-hosted coding agent daemon that turns Linear tickets into pull requests using isolated AI agents

CLI for playing games on the Prompted platform. Build AI agents that play poker, Secret Hitler, Coup, Skull, and Liar's Dice.

Lightweight multi-agent orchestration framework supporting parallel execution, loops, and iterative execution.

AgentWallex CLI — manage AI agent payments from the command line

Read-only Jira connector: JQL search, issue details, project metadata. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.

Read-only GitHub connector: repo info, code search, PR/issue listing, file retrieval. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.

Read-only Confluence connector: CQL search, spaces, pages. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.

Read-only Notion connector: search, pages, databases. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.

Multi-tier exact-match cache for AI agent workloads backed by Valkey. LLM responses, tool results, and session state with built-in OpenTelemetry and Prometheus instrumentation.

SpawnHub adapter for the OpenAI Agents SDK

A pip-installable benchmark runner for LLMs and agents. 5 minutes to your first eval.

Multi-Agent Chatbot SDK - Build customizable multi-agent chatbots with ease

An agent factory with dynamic DAG scheduling for multi-agent task coordination

PayClaw tools for LlamaIndex — give your FunctionAgent / ReActAgent a USDC wallet on Base it can actually spend. Gasless via Circle Paymaster.

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.

Webhook routing + Claude Agent SDK observability