humanlayer / agentcontrolplaneLinks
ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.
☆125Updated last month
Alternatives and similar repositories for agentcontrolplane
Users that are interested in agentcontrolplane are comparing it to the libraries listed below
Sorting:
- Augment Swarm with durable execution to help you build reliable and scalable multi-agent systems.☆102Updated 8 months ago
- Routing on Random Forest (RoRF)☆181Updated 10 months ago
- 🤖 Headless IDE for AI agents☆196Updated 3 months ago
- ☆98Updated last month
- Modular, open source LLMOps stack that separates concerns: LiteLLM unifies LLM APIs, manages routing and cost controls, and ensures high-…☆107Updated 5 months ago
- A Node.js package and GitHub Action for evaluating MCP (Model Context Protocol) tool implementations using LLM-based scoring. This helps …☆76Updated last month
- A plan engine for dynamic planning and reliable execution of AI agent workflows.☆222Updated 2 months ago
- A toolkit for building computer use AI agents☆170Updated last month
- Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol☆135Updated 2 months ago
- Model Context Protocol (MCP) Server for Langfuse Prompt Management. This server allows you to access and manage your Langfuse prompts thr…☆123Updated 5 months ago
- MarinaBox is a toolkit for creating and managing secure, isolated environments for AI agents☆135Updated 5 months ago
- Provider-agnostic, open-source evaluation infrastructure for language models☆203Updated this week
- A specification language for AI-first development that shifts focus from implementation to intent through structured solution space reduc…☆100Updated 3 weeks ago
- MCP (Model Context Protocol) server for Weaviate☆139Updated 2 months ago
- A framework for building large-scale, deterministic, interactive workflows with a fault-tolerant, conversational UX☆18Updated this week
- A daemon that makes a desktop OS accessible to AI agents☆33Updated 2 months ago
- Official servlets for mcp.run published by @dylibso☆61Updated 2 weeks ago
- Securely run AI-generated code in stateful sandboxes that run forever.☆212Updated 3 months ago
- Enriched Python function call graphs for agents and coding assistants☆101Updated last month
- Making APIs accessible to AI Codegen☆50Updated 3 months ago
- Anthropic Computer Use with Modal Sandboxes☆37Updated 9 months ago
- An HTTP service intended as a backend for an LLM that can run arbitrary pieces of Python code.☆65Updated last month
- FACT – Fast Augmented Context Tools: FACT is a lean retrieval pattern that skips vector search. We cache every static token inside Claude…☆75Updated 2 months ago
- A prompt management, versioning, testing, and evaluation inference server and UI toolkit. Provider agnostic and OpenAI API compatible.☆114Updated last month
- Open-source AI copilot that lets you chat with your observability data and code 🧙♂️☆353Updated 3 months ago
- a Python library that uses Reinforcement Learning (RL) to train LLMs.☆38Updated this week
- Not Diamond Python SDK☆83Updated last month
- ☆129Updated last month
- MCP Tools Langraph Integration☆45Updated 4 months ago
- Letting Claude Code develop his own MCP tools :)☆122Updated 4 months ago