Autonomous AI agents that perform tasks independently
teknium
Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company
GitHub Actions
Teach your AI agent the Nuxt way with best practices and module guidance.
niaka3dayo
AI Agent Skills for VRChat UdonSharp - Rules, validation hooks, and knowledge base for correct UdonSharp code generation
arash.em
Kraken AI SDK: a very lightweight, fully-typed multi-model AI agent framework
elonehoo
A lightweight embedded agent framework (similar to Claude Code and OpenAI Codex).
graypark
Ralph Loop for Codex CLI & Claude Code — iterative dev loops with multi-agent orchestration, interactive interview, and stop hooks
...morebrickee
OpenClaw plugin — cross-process dedup cache for multi-agent tool calls via SQLite sidecar
samwang0723
Pixel-art dashboard for Claude Code multi-agent teams — real-time agent statuses, messaging, and activity via WebSocket
codesharpdev
Shared code intelligence infrastructure for AI agents. LSP for AI.
lizi_xiaoming
ContextEngine plugin for OpenClaw with retrieval-augmented context management and memory-aware compaction
wangbobo1225
Kubernetes Sidecar browser automation tool for OpenClaw
Python SDK for TendedLoop Arena — multi-agent gamification research platform
SDK for publishing AI-generated images to the AI·gram social platform
rukkiecodes <[email protected]>
RukkiePulse agent SDK — auto-instrument Python services and push telemetry to Jaeger
OpenTrace Contributors
OpenTrace Python agent — maps system architecture, code structure, and service relationships into a knowledge graph
OpenTelemetry OpenAI Agents instrumentation
Neuralchemy
The Secure-by-Default Execution Framework for LLM Agents.
Building blocks for rapid development of GenAI applications
Agent Runtime for production — LLM-native execution with tools, budget, and trace built in.
A framework for orchestrating applications powered by autonomous AI agents and LLMs.
A secure sandbox execution environment for DB-GPT Agent
CrewAI memory integration via Hindsight - persistent memory for AI agent crews
Universal LLM memory integration via LiteLLM - works with 100+ providers
Multi-agent code review CLI powered by LLMs. Runs specialized agents in parallel to review GitHub PRs or local diffs.