An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
Open source
24 alternativesAgentField
AgentField lets developers build, run, and scale AI agents as APIs and microservices.
About AgentField
AgentField is an open-source control plane for building AI agents that other services can call like any API. Developers write agent logic in Python, Go, or TypeScript, and AgentField exposes each function as a REST endpoint. The homepage says it provides routing, coordination, memory, async execution, and observability for these agents. One request can fan out to many agents, with the control plane handling queues, retries, and tracing for each branch. The homepage describes the same code running from one agent on a laptop to ten thousand agents in a single workflow.
Setup is done with a shell installer from agentfield.ai, which adds the af command-line tool and an optional aforge coding harness. On macOS, the installer also registers the control plane to start at login and adds a menu-bar icon, and both can be skipped with a flag. The homepage also describes a /agentfield command that generates a Docker Compose stack for a multi-agent backend from a written spec. Pricing is not stated.
Key features
- Each function becomes a REST endpoint callable by services, cron jobs, or other agents
- Agent logic written in Python, Go, or TypeScript
- Fan-out of one request to many agents, with queuing and retries
- Tracing of every branch in a multi-agent workflow
- Generation of a Docker Compose multi-agent backend from a written spec
- Version setting noted for canary deploys, A/B testing, and blue-green rollouts
Best for: Developers who want to run AI agents as APIs or microservices that other services in their stack can call.
Good for
- Agents are exposed as REST endpoints, so existing services can call them like any other API.
- Routing, coordination, memory, async execution, and observability are described as part of one control plane.
- Open source, with a LICENSE file in the repository.
Watch out for
- On macOS, a plain kill of the control plane causes it to restart, so af service stop or the menu-bar icon must be used to stop it.
- The macOS installer registers the control plane to start at login unless the --no-tray option is used.
AgentField at a glance
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
AgentField alternatives
Tools and sites you could use instead, ranked by how closely they match.
The LangChain repository describes an agent engineering platform for building agent based software.
Open source
24 alternatives
Mem0 provides persistent memory infrastructure for AI agents and applications.
Open source
24 alternatives
Upsonic provides a Python framework for creating autonomous AI agents.
Open source
24 alternatives
EvoAgentX describes its project as an ecosystem of AI agents that can evolve over time.
Quivr provides retrieval augmented generation for integrating generative AI into apps, with support for multiple models and vector stores.
Popular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
AgentField FAQ
Which languages can I use to write agent logic?
The homepage lists Python, Go, and TypeScript, with SDKs for each.
What does the installer add to my system?
It installs the af command-line tool and an optional aforge coding harness in ~/.agentfield/bin. On macOS it also registers the control plane to start at login and adds a menu-bar icon, unless --no-tray is used.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.