Alpha preview: pin 3.0.0a3 when you install. A bare pip install agentbreeder still installs the unmaintained 2.x: known issues.
agentbreeder

Registry

Immutable, hash-locked versions of prompts, tools, knowledge, eval sets, MCP servers, services, runtimes and released agents: show, diff, import, fork, edit.

Preview

The commands below ran on macOS with Docker Desktop against Northwind and starter projects, from a wheel built from main. Skills are on main for authoring only; no runtime loads them yet.

A registry is a directory of immutable, versioned building blocks, referenced as kind/name@X.Y.Z. AgentBreeder looks in the project's ./registry, then AGENTBREEDER_REGISTRY_PATH, then the versions it ships. The same ref with different content in two places is an error, never a silent shadow. agent.lock records each ref's hash, and build --locked refuses any change.

KindHolds
promptthe system prompt text
toolPython functions the runtime loads (code)
knowledgedocuments the runtime indexes into pgvector
evalcases, a judge alias and optional fixtures SQL (code)
mcpan MCP server definition for the relay (code)
servicea backing service for stack.yaml (code)
runtimethe agent runtime, such as runtime/adk@1.4.0 (code)
agenta released agent package, written only by release
skillinstructions or scripts for a later runtime; see Sub-agents and skills

Read

agentbreeder registry list
agentbreeder registry show tool/orders@1.0.0          # manifest, files, a tool's functions
agentbreeder registry diff prompt/p@1.0.0 prompt/p@1.0.1
agentbreeder registry used-by tool/orders@1.0.0       # declared, locked and deployed
agentbreeder registry verify

show reads a tool's function signatures without importing its code.

Write

agentbreeder registry new tool orders                       # scaffold, then edit
agentbreeder registry publish ./tool-orders
agentbreeder registry import PATH --dry-run --json          # review, then --expect-digest
agentbreeder registry fork service/echo@1.0.0 --as my-echo  # copy a built-in into the project
agentbreeder registry edit prompt/p@1.0.0 --set prompt.md NEW.md --dry-run
agentbreeder agent set-ref prompt/p@1.0.0 prompt/p@1.0.1    # point agent.yaml at it

Every write makes a new version; nothing is overwritten (VERSION_EXISTS). Import and edit can be bound to the reviewed digest (--expect-digest), so what is written is exactly what was shown. A tool version is checked before it is written (TOOL_INVALID): only its manifest, tool.yaml, README* and src/**/*.py, no module that shadows the standard library or the runtime, and every function a parsable top-level def. Kinds marked code above run inside agents, and the CLI and console say so before importing or forking one.

Inspect a running agent's parts

agentbreeder tool log tool/orders --project .         # recorded calls; arguments only with --content
agentbreeder knowledge status knowledge/help --project .   # not_indexed, fresh or stale, with chunk counts

tool log shows what the runtime recorded: the agent's database role can insert any row, and MCP tool calls are not in it.

In the console

Registry lists prompts, eval sets, tools, knowledge, MCP servers, services and runtimes, with versions, diffs and used-by (not skills or agent packages yet). Project prompts, eval cases, tool code and knowledge documents open in editors that save a new version after a review, then offer Move agent to this version and Build and update agent.lock. Import and fork ask the "this code runs in agents" confirm for code kinds. Tool pages and their editor are tested in CI but have not been run against a live stack.

Limits

  • Hashes detect a change after a version is first locked; they don't vouch for that first lock.
  • Tools run in the agent's process with its privileges. Customer scoping is the tools' own code.
  • An agent package is a record, not a credential. It is not signed.

Canonical reference: registry.md.

On this page