OpenAgentd

A desktop coding agent that runs on your own machine and shows every tool call, diff and terminal command.

Stars
★ 217
Last updated
1d ago
License
Apache-2.0
Primary language
TypeScript

At a glance

How it runs
Desktop appCLISelf-hosted service
Works with
Universal · cross-platformChatGPT · OpenAI API · Claude API
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
macOS or Linux or Windows desktop OSA model provider account or API key, or a local Ollama installOptional: HTTPS reverse proxy for exposing the CLI server outside a trusted networkShell / CLINetwork accessLocal filesystemMCP Server
Typical use
A solo developer who wants the agent to finish one concrete job on their laptop — such as adding rate limiting to a small Bun service and running the suite — then reviews the uncommitted diff before committing.
Not a fit if
  • Teams that need unattended CI runs on headless servers with no desktop environment
  • Operators who need built-in TLS before exposing a service to the public internet
  • Users who want one fixed vendor model and no bring-your-own-key setup
Website
openagentd.dev ↗ set on GitHub
Maintenance
Commits in the last 30 dayslast commit 2026-11-20latest release v3.61.0 (2026-11-18)

What does this agent do, and when should you use it?

OpenAgentd is a local-first desktop app for running a coding agent on your own computer: you hand it a folder and a task, and it plans, reads, edits, runs your tests and shows every step — each tool call with its arguments and timing, every diff, and what each turn costs. It is powered by a single native Rust backend (a 46 MB binary that starts in about 50 ms), and the desktop app launches that backend itself, so sessions, settings and telemetry stay on your machine. It ships with 18 built-in model providers (Anthropic, OpenAI, Gemini, OpenRouter, Bedrock, DeepSeek and more), works with an existing ChatGPT, Copilot or Grok subscription, and runs local models through Ollama. Work is split into Plan mode, where the agent explores read-only and writes a plan you can comment on and approve, and Code mode, where you can steer, queue or stop a running turn. Beyond the desktop app, a CLI-only install provides an agentd backend and server that phone and desktop clients can connect to, and MCP servers, skills and plugins extend what the agent can reach.

After you open a folder and describe a task, the agent reads the repository and plans. In Plan mode it explores read-only and writes a plan with a "Done when" condition; you select any passage to comment on it, then Approve, or use Reply in chat to send the comments as a normal message. In Code mode it executes directly and you can steer, queue or stop the running turn. While working it calls tools to read and edit files and to run shell commands and tests; every tool call with its arguments and timing, shell output, file diffs, todos, tokens and cost streams into one transcript, which Reader mode can collapse to just the answers. A lead agent can delegate focused jobs to subagents such as explorer#1, /btw answers side questions in its own panel without entering the agent's context, and language-server diagnostics appear after edits. Repository features include Git changes, history and graph, worktrees, a real terminal and a live preview of your web app. The agentd CLI runs the backend headless — agentd server start serves the API (add --public --key --qr to pair a phone, or --cloud for remote control), and agentd run / agentd run --continue execute tasks — while the iOS and Android apps pair by QR code and show the same sessions.

  1. A solo developer who wants the agent to finish one concrete job on their laptop — such as adding rate limiting to a small Bun service and running the suite — then reviews the uncommitted diff before committing.
  2. Teams that want an approved plan before any code changes: generate the plan in Plan mode, discuss it with inline comments, then approve and let the agent work until the plan's Done when is proven.
  3. Users who want model costs on their own accounts: use an existing ChatGPT, Copilot or Grok subscription, or run local models through Ollama instead of committing to one vendor.
  4. A developer away from the desk who wants to keep following the task: pair a phone with the desktop app or an agentd server to view the same sessions, answer questions, approve plans or stop a run.
  5. Anyone who needs to ask a clarifying question without polluting the main context: /btw opens a separate panel whose answer never enters the agent's context.
  6. Teams extending the agent's reach by connecting MCP servers, adding skills and plugins, or chaining many tool calls in one scripted step.

Key setup facts

Pulled from the install and usage notes below. The project README has the current values.

Install / run
  • curl -fsSL https://openagentd.dev/install.sh | sh
  • irm https://openagentd.dev/install.ps1 | iex
  • brew install --cask lthoangg/tap/openagentd
  • curl -fsSL https://openagentd.dev/install.sh | sh -s -- --cli
Install notes cover
Windows · macOS · Linux

How do you install or deploy this agent?

On macOS and Linux use the install script:

curl -fsSL https://openagentd.dev/install.sh | sh

On Windows (PowerShell):

irm https://openagentd.dev/install.ps1 | iex

On macOS you can also use Homebrew:

brew install --cask lthoangg/tap/openagentd

To install only the backend, for terminal use or to serve other devices:

curl -fsSL https://openagentd.dev/install.sh | sh -s -- --cli

Windows PowerShell CLI install:

& ([scriptblock]::Create((irm https://openagentd.dev/install.ps1))) -Cli

Platform builds are on the releases page; unsigned builds may ask you to confirm before the first launch. Building from source is described in the Quick start section of CONTRIBUTING.md.

How do you use this agent?

Open OpenAgentd and connect a model on the first screen: paste an API key, sign in with a ChatGPT or Copilot subscription, or press Use on a key or Ollama install it finds. Then open a folder and describe what you want built; the desktop app starts its own backend, so there is nothing else to run.

Press Tab in the composer to switch between Plan and Code modes. In Plan mode, review the plan, select a passage to comment, then Approve, or use Reply in chat to send your comments as a normal message. From a terminal, use the CLI:

agentd server start
agentd run "Summarize this project"
agentd run --continue "Now add tests for it"

Add --public --key --qr to server start to pair a phone, or --cloud to enable remote control; agentd --help lists every command. The server serves the API only and has no built-in TLS, so put an HTTPS reverse proxy in front of it before exposing it outside a trusted network.

What are this agent's strengths and limitations?

Pros
  • Full visibility: tool calls with arguments and timing, shell output, diffs, tokens and cost land in a single transcript, and Reader mode keeps just the answers.
  • Plan-then-act control: Plan mode explores read-only and produces a commentable plan; after approval the agent keeps working until the plan's Done when condition is proven.
  • Provider choice: 18 built-in providers plus existing ChatGPT/Copilot/Grok subscriptions and local models via Ollama, with plugins able to add more.
  • Local-first and small: one Rust backend, a 46 MB binary starting in about 50 ms, with sessions, settings and telemetry kept on the machine.
  • Built for real repositories: Git changes, history and graph, worktrees, a real terminal, a live web preview and language-server diagnostics after edits.
  • The same sessions extend to phones: pair by QR code and reply, approve or stop the agent from iOS or Android, with optional remote control.
Limitations
  • Model usage is not included: you need your own provider key, subscription or local Ollama install, and costs depend on the model you choose.
  • The CLI server has no built-in TLS; you must deploy an HTTPS reverse proxy before exposing it beyond a trusted network.
  • Unsigned builds may trigger OS confirmation on first launch, which adds friction for managed or enterprise distribution.
  • Mobile use depends on pairing with the desktop app or configuring remote control; it is not a standalone cloud service.
  • Automatic work after plan approval depends on the plan's stated Done when condition, so plan quality directly governs how safe the unattended run is.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
OpenAgentd This agent 53 · Major gaps Desktop appFree + model costs ★ 217 1d ago TypeScript ChatGPT · OpenAI API · Claude API
Ogcode 50 · Major gaps CLIFree + model costs ★ 148 3d ago Go OpenAI API · Claude API
Pi Agent Desktop 78 · Good — ★ 353 9d ago TypeScript OpenAI API
Synara 57 · Major gaps Desktop appFree + model costs ★ 2.3k 1d ago TypeScript Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
53/ 100 5-point scale 2.7 / 5
Trust 17/29
Reliability 6/14
Adaptability 10/18
Convention 9/18
Effectiveness 7/13
Verifiability 4/8
Why each dimension lost points
Trust17 / 29 · 2.9/5

SECURITY.md and AGENTS.md document constant-time key comparison, network guard, workspace validation, path-traversal protection, argument-list subprocesses, 0600 atomic credential writes, and request size caps, giving solid static evidence for least_privilege/user_confirmation/data_flow_transparency/sensitive_data_handling at 2; deductions for plaintext credentials without OS keychain and a lexical-only (non-sandbox) shell check. dependency_security gets 2 for cargo audit and locked builds in cloud.yml, but only three Rust lockfiles are audited and web/Bun dependencies are not covered. external_effects gets 2 for Plan mode and pre-commit review, though AGENTS.md lets the agent commit locally (reversible). rollback gets 1: only git commits and update verification are shown, no session/file-level rollback. source_attribution gets 1: README and LICENSE only, no NOTICE or third-party attribution.

Reliability6 / 14 · 2.1/5

self_consistency gets 2: README, AGENTS.md, and SECURITY.md agree on architecture and security boundaries. dependency_availability gets 1: Bun 1.4.0, Rust, cargo-nextest, python3, lsof/nc are listed but without lockfile detail or fallback paths. failure_messages gets 1: only drive.sh doctor and scattered code comments show error handling conventions; no systematic failure-message standard.

Adaptability10 / 18 · 2.8/5

audience_and_scenarios gets 2: desktop, CLI, mobile, and multiple providers are clearly covered. capability_boundaries gets 2: Plan/Code modes, read-only exploration, and approval flow define boundaries. trigger_precision gets 1: SKILL.md descriptions are broad (e.g. guidelines triggers on writing/reviewing/refactoring code) without precise triggers. environment_fit gets 2: macOS/Linux/Windows install paths and Tauri system dependencies are stated.

Convention9 / 18 · 2.5/5

information_architecture gets 2: README, layered AGENTS.md instructions, and documents/docs/features.md index. install_notes gets 2: curl, brew, PowerShell, and CLI install paths. naming_stability gets 1: no versioned naming or deprecation policy shown. examples_and_faq gets 1: only a quick tour with screenshots, no FAQ. known_limitations gets 2: SECURITY.md and README disclose no built-in TLS, non-sandbox shell check, plaintext credentials. license gets 2: full Apache-2.0 text. versioning_changelog gets 1: releases and version-cited features exist but no in-repo CHANGELOG. maintenance_responsibility gets 1: publisher unverified and SECURITY.md only promises best-effort response.

Effectiveness7 / 13 · 2.7/5

output_usability gets 2: transcript, diffs, cost display, and Reader mode improve usability. marginal_value gets 2: local-first, multi-provider, mobile, and observability differentiate it from generic coding agents. cost_benefit gets 1: 46MB/50ms claims lack benchmark evidence and users must supply model keys, so cost-benefit is asserted rather than shown.

Verifiability4 / 8 · 2.5/5

claim_traceability gets 1: many README claims point to SECURITY.md and contract docs, but performance claims (46MB, 50ms) have no supporting evidence. cross_source_corroboration gets 2: README, SECURITY.md, AGENTS.md, and CI workflows corroborate security and testing claims. fact_inference_separation gets 1: docs blend philosophy with facts and do not clearly separate inference from verified fact.

Risks and how to mitigate them
  • Credentials are stored plaintext with 0600 in credentials.yaml, no OS keychain; the shell file guard is lexical, not an OS sandbox, so agent commands can still reach sensitive files indirectly.
  • The CLI server has no built-in TLS; an HTTPS reverse proxy is required before exposing it beyond a trusted network.
  • Publisher identity is unverified and maintenance is best-effort only; enterprises should verify before adoption.
  • Dependency auditing covers only three Rust lockfiles; web/Bun dependencies are unaudited, and performance claims (46MB/50ms) lack benchmark evidence.
  • AGENTS.md lets the agent commit locally; reversible but teams should confirm they accept automated commits.
Evidence confidence: Low Reviewed Nov 20, 2026 Reviewed revision c7c906dc7851
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/openagentd.svg)](https://followagents.com/en/agents/openagentd)
<a href="https://followagents.com/en/agents/openagentd"><img src="https://followagents.com/badge/openagentd.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v3.61.0
    Release notes excerpt
    What's changed - Remote control on Android. The Android app (Android 11 or later, with a screen lock) can sign in to your account or join it by scanning a code, add and approve devices, and open your computers through your account or directly on your home network, as the iPhone app does. Its keys stay in the Android Keystore, and approving, adding or removing a device asks for your fingerprint or screen lock. Done, Needs you and Failed notifications from your other computers arrive as pushes. …
    View on GitHub ↗
  2. v3.60.0
    Release notes excerpt
    What's changed - A cleaner Connectors page, with logos. Settings → Connectors now lists your own connectors first, each with the service's logo, its status, a switch and Connect, followed by a compact gallery of the ones you have not added, under one search box. Added connectors no longer show twice. The composer's "+" menu shows full names, a status line and one-line errors (the full text on hover), and says "Connect" instead of "Sign in". …
    View on GitHub ↗
  3. v3.59.0
    Release notes excerpt
    What's changed - Keys without exposing them. When a task needs an API key or token, the agent asks for it on a card. You paste the value once, on your computer or your phone, and choose which projects may use it. The agent, the transcript and the logs only ever see [secret NAME], and two projects can keep different values under the same name. Settings → Secrets lists what is stored. - Plan comments go to the chat. In a plan review, Reply in chat moves your comments into the message box, so your feedback shows in the conversation. The Plan panel's separate feedback box is gone. …
    View on GitHub ↗

FAQ

Do I have to pay for OpenAgentd itself?
The app is open source under Apache 2.0; the cost is inference. You can use paid API keys from providers such as Anthropic, OpenAI or Gemini, an existing ChatGPT, Copilot or Grok subscription, or local models through Ollama.
Does my code or session data leave my machine?
Sessions, settings and telemetry stay local by default, and other devices connect only when you turn on network access or sign in to remote control. Model requests themselves go to whichever provider you configure; pair with Ollama if you need everything local.
Can I stop the agent while it is running commands?
Yes. Plan mode is read-only and requires your approval before execution, and in Code mode you can steer, queue or stop a running turn. Changes are left uncommitted as a diff for you to review.
How do I run it headless on a server?
Install the CLI variant and run agentd server start, which serves the API for desktop and mobile clients to connect to at the printed Server address. There is no built-in TLS, so add an HTTPS reverse proxy if you need to reach it from outside a trusted network.
Can I wire in my own tools?
Yes — connect MCP servers, add skills and plugins, and let the agent chain many tool calls in one scripted step.
Does OpenAgentd work on Windows?
Yes. The install notes on this page include a Windows command: irm https://openagentd.dev/install.ps1 | iex.
Is OpenAgentd open source?
Yes. The source code is on GitHub (lthoangg/OpenAgentd) under the Apache-2.0 licence.
Is OpenAgentd safe to use?
FollowAgents' FARS review (Nov 20, 2026) scored OpenAgentd 17/29 on trust and safety. None of the eight safety controls the review checks for was missing outright.
Is OpenAgentd still maintained?
Yes. The latest commit on GitHub is from 2026-11-20, within the last 30 days. The latest release is v3.61.0 (2026-11-18).
Who makes OpenAgentd?
OpenAgentd is published on GitHub by the account lthoangg. FollowAgents has not verified which person or company is behind that account.
What is OpenAgentd's official website?
The project's GitHub repository lists https://openagentd.dev as its website. That link is set by the repository owner; the source code itself is on GitHub (lthoangg/OpenAgentd).
Was this page helpful?
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related concepts