Skip to content

About

Open-source runtime for AI agents that wake on production events, investigate with your logs, metrics and code, and prepare a fix you approve.

Topics

Resources

Security policy

Stars

6 stars

Watchers

1 watching

Forks

Latest commit

 

History

8,578 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

agentsfleet

AI agents that wake when production breaks.

CI rust-afd coverage app coverage website coverage cli coverage Rust Docs License: MIT

agentsfleet is an open-source runtime for agents configured for recurring jobs. Each fleet has instructions, tools, triggers, access rules, and a budget. Events or messages wake the fleet; runners investigate with its permitted tools and save the results.

  • Controlled access — tools and network rules determine which actions a fleet can perform.
  • Durable results — event history records requests, outcomes, and reports; live activity shows work in progress.
  • Model choice — use the platform model or an account model configured with your own provider key.
  • Separate working instances — each fleet keeps its own history and memory.

You write a fleet by describing the job in a private chat, in the app or with agentsfleet chat. The chat drafts a typed Definition you review, then Save creates the fleet and checks its access. See fleet definitions.


Quick start

Already invited? Sign in to the app. To request access, visit Early access.

The public command-line interface (CLI) package is waiting for release. Build the CLI from this repository with Bun 1.4 or newer:

git clone https://github.com/agentsfleet/agentsfleet.git
cd agentsfleet/cli
bun install
bun run build
bun ./dist/bin/agentsfleet.js login

Sign in in the browser, then enter the browser's verification code in the terminal. The CLI reports login complete after verification.

See the CLI install guide for installer and release instructions. The quickstart covers writing a fleet in chat and connecting its tools and triggers.


What's in this repo

Directory What
rustd/ Rust workspace — the agentsfleetd control plane (afd_* crates, one per plane) and the agentsfleet-runner execution daemon (afr_* crates).
ui/packages/app/ Dashboard — Next.js, Clerk auth
ui/packages/website/ Marketing site — agentsfleet.net
ui/packages/design-system/ Shared UI components
cli/ Command-line interface (CLI) — install, manage agents, tail runs
public/openapi.json OpenAPI reference generated from the daemon's route and schema definitions
schema/ Postgres migrations
playbooks/ First setup, deployment, verification, and operations

Local development

Prerequisites: Rust 1.99.1 (pinned by rustd/rust-toolchain.toml, which rustup installs on the first cargo run inside rustd/) · Docker (Postgres, Dragonfly, QStash) · Bun ≥1.4 · Clerk dev project · 1Password CLI for secrets

git clone https://github.com/agentsfleet/agentsfleet.git
cd agentsfleet

# Run provision-env-1password first. See docs/development.md for shared-worktree setup.
make up           # Shared services + this worktree's native daemon; migrate before serving

# Install in this order. The root install alone does NOT reach the workspace
# packages, and the coverage lane then fails resolving `next/headers` — a
# failure that reads like a code defect and is not one.
bun install
(cd cli && bun install && bun run build)
for pkg in ui/packages/*/; do (cd "$pkg" && bun install); done

export NEXT_PUBLIC_API_URL="$(bash scripts/local-dev.sh url)"
cd ui/packages/app && bun run dev

Run provision-env-1password before local tests. The shell sources ~/.config/agentsfleet/.env, which names the UI, runner, and daemon files under that directory through AGENTSFLEET_UI_ENV_FILE, AGENTSFLEET_RUNNER_ENV_FILE, and AGENTSFLEET_RUSTD_ENV_FILE. Local UI and daemon tests read their files directly; the runner path is available to tests that need it. No worktree environment-file symlinks are needed. The app refuses to guess a backend when NEXT_PUBLIC_API_URL is unset.

See shared development worktrees for startup, status, ownership and teardown.

Verify:

make lint-all
make test-unit-all
make test-integration-rustd   # needs Docker: live Postgres + Dragonfly

CLI

agentsfleet defaults to production. From the repository root, select this worktree's URL with --api or the environment. Replace <COMMAND> with your command.

agentsfleet --api "$(bash scripts/local-dev.sh url)" <COMMAND>
export AGENTSFLEET_API_URL="$(bash scripts/local-dev.sh url)"

Contributing

git config core.hooksPath .githooks

Project facts live in AGENTS.md. The operating model and the deterministic gate scripts are committed alongside them — .orly/AGENTS.md, .orly/dispatch/, and .orly/audits/ — materialised by orly and recorded in .orly/orly.json. A clone carries its own rules; nothing resolves out of a developer's home directory.

Install orly at the version this repository records, so a local run and Continuous Integration grade against the same rules:

npm install -g "@agentsfleet/orly@$(jq -r .orly_version .orly/orly.json)"

orly doctor                     # report drift between the lock and the tree
orly update --no-hooks          # re-materialise at the installed version
orly gate work                  # what the pre-commit hook runs

--no-hooks is not optional here: this repository owns .githooks/pre-commit and .githooks/pre-push, and orly declines to overwrite hooks it did not write.

make harness-verify runs shared gates from .orly/audits/ and repository-owned checks from audits/.

Read about architecture, start with the operator playbooks, or jump into local development.


MIT — Copyright (c) 2026 agentsfleet.

About

Open-source runtime for AI agents that wake on production events, investigate with your logs, metrics and code, and prepare a fix you approve.

Topics

Resources

Security policy

Stars

6 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages