Agent-Field/agentfield
Build, run and scale AI agents like API and microservices
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Quick read
Latest capture 2026-09-04 04:09
768 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 9
Agent workspace 284
Claude Code 475
744 more paths detected.
101 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +16066
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Build, run and scale AI agents like API and microservices
Open-source control plane for AI coding agents. Run an AI engineering team: parallel Claude Code, Codex, and Gemini workers with a shared board, atomic tasks, schedules, loops, origin-stamped messaging, model switching, and self-healing recovery. One dashboard, or your phone. MIT, single Rust binary.
Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.
Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.
Your Company Agentic Operating System