内容摘录
<div align="center">
<img src="assets/github hero.png" alt="AgentField - Kubernetes, for AI Agents" width="100%" />
Kubernetes for AI Agents
**Deploy, Scale, Observe, and Prove.**
*When AI moves from chatbots into backends, making decisions, not just answering questions, it needs infrastructure, not frameworks.*
License
Downloads
Last Commit
Go
Python
Deploy with Docker
Discord
**Docs** | **Quick Start** | **Python SDK** | **Go SDK** | **TypeScript SDK** | **REST API** | **Discord**
</div>
What is AgentField?
**AgentField is the backend infrastructure layer for autonomous AI.**
AI has outgrown frameworks and is moving from chatbots into backends—making decisions about refunds, coordinating supply chains, managing portfolios. These agents need infrastructure, not prompt wrappers.
AgentField is an open-source **control plane** that treats AI agents as first-class backend services and makes agents production-ready.
**Scale Infrastructure** *(think: Kubernetes)*
**Routing & Discovery**: Agents find and call each other through standard REST APIs
**Async Execution**: Fire-and-forget tasks that run for minutes, hours, or days
**Durable State**: Built-in memory with vector search—no Redis or Pinecone required
**Observability**: Automatic workflow DAGs, Prometheus metrics, structured logs
**Trust Infrastructure** *(think: Okta, rebuilt for agents)*
**W3C DIDs**: Every agent gets a cryptographic identity—not a shared API key
**Verifiable Credentials**: Tamper-proof audit trails for every action
**Policy Enforcement**: Boundaries enforced by infrastructure, not prompts
Write Python, Go, TypeScript, or call via REST. Get production infrastructure automatically.
---
The AI Backend
Software keeps adding layers when complexity demands it. Frontend/backend separation. Data lakes and pipelines. Now: a **reasoning layer** that sits alongside your services, making decisions that used to be hardcoded.
We call this the AI Backend. Not a chatbot, not a copilot—infrastructure for software that can think.
**Guided autonomy:** Agents that reason freely within boundaries you define. Predictable enough to trust. Flexible enough to be useful.
📖 **Read: The AI Backend** — Our thesis on why every serious backend will need a reasoning layer.
---
See It In Action
<div align="center">
<img src="assets/UI.png" alt="AgentField Dashboard" width="100%" />
<br/>
<i>Real-time Observability • Execution Flow • Audit Trails</i>
</div>
---
Build Agents in Any Language
<details open>
<summary><strong>Python</strong></summary>
Full Python SDK Documentation →
</details>
<details>
<summary><strong>Go</strong></summary>
Full Go SDK Documentation →
</details>
<details>
<summary><strong>TypeScript</strong></summary>
Full TypeScript SDK Documentation →
</details>
<details>
<summary><strong>REST / Any Language</strong></summary>
REST API Reference →
</details>
---
Quick Start
Install
Create Your Agent
Start (Two Terminals Required)
AgentField uses a **control plane + agent node** architecture. You'll need two terminal windows:
**Terminal 1 – Start the Control Plane:**
Opens the dashboard at http://localhost:8080
**Terminal 2 – Start Your Agent:**
Agent auto-registers with the control plane
Test It
<details>
<summary><strong>Other Languages / Options</strong></summary>
**Go:**
**TypeScript:**
**Interactive mode** (choose language, set author info):
</details>
<details>
<summary><strong>Docker / Troubleshooting</strong></summary>
If running the **control plane in Docker** and your **agent node runs outside that container**, make sure the control plane can reach the agent at the URL it registers.
**Option A (agent on your host, control plane in Docker):**
**Option B (agent + control plane both in Docker Compose / same network):**
Set the agent callback/public URL to the agent container's service name, e.g. http://my-agent:8001.
**Linux note:** host.docker.internal may require --add-host=host.docker.internal:host-gateway or using a Compose setup where both containers share a network.
</details>
**Next Steps:** Build Your First Agent | Deploy to Production | Examples
---
Production Examples
Real-world patterns built on AgentField:
| Example | Description | Links |
|---------|-------------|-------|
| **SWE-AF** | Autonomous software engineering factory. One API call spins up a full engineering fleet — PM, architect, coders, QA, reviewers, merger — that plans, builds, tests, and ships complex software end-to-end. Scored **95/100** with haiku, outperforming Claude Code sonnet (73) and Codex (62) on the same benchmark. Ships real PRs: PR #179 was built entirely by SWE-AF (10 issues, 217 tests passing, $19.23 total cost). | GitHub |
| **Deep Research API** | Massively parallel research backend. Fans out to 10k+ agents, synthesizing verifiable strategies with deep citation chains. | GitHub • Docs |
| **RAG Evaluator** | Production monitoring for LLM responses. Scores across 4 dimensions to identify reliability issues. | Architecture |
See all examples →
---
The Production Gap
Most frameworks stop at "make the LLM call." But production agents need:
See the production-ready feature set →
Scale & Reliability
Agents that run for hours or days. Webhooks with automatic retries. Backpressure handling when downstream services are slow.
Multi-Agent Coordination
Agents that discover and invoke each other through the control plane. Every call tracked. Every workflow visualized as a DAG.
Developer Experience
Standard REST APIs. No magic abstractions. Build agents the way you build microservices.
Enterprise Ready
Cryptographic identity for every agent. Tamper-proof audit trails for every action. Learn more about Identity & Trust.
---
A New Backend Paradigm
AgentField isn't a framework you extend. It's infrastructure you deploy on.
See how AgentField compares to agent frameworks →
| | Agent Frameworks | DAG/Workflow Engines | AgentField |
| ------------------ | -------------------------- | --------------------…