OpenAgent Terminal Agent

Plan and execute terminal tasks with local, free, or bring-your-own-key models.

Stars
★ 279
Last updated
8d ago
License
Apache-2.0
Primary language
TypeScript

At a glance

How it runs
CLI
Works with
Universal · cross-platformOpenAI API · Claude API
Cost
Free, no paid service needed
Setup effort
Low · running in minutes
You'll need
Node.js 22+Shell / CLINetwork accessLocal filesystemMCP Server
Typical use
A data practitioner who wants to inspect a local CSV and produce a chart from a terminal prompt.
Not a fit if
  • Users who require a graphical desktop or web interface
  • Environments unable to install Node.js 22+
  • Teams requiring multi-provider work solely from the default branch
Maintenance
Commits in the last 30 dayslast commit 2026-11-12latest release v4.1.4 (2026-07-31)

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

OpenAgent is an open-source terminal agent for Windows, macOS, and Linux that accepts a task in plain English, plans the work, uses tools, and returns the result. It is distributed as an npm CLI and can also be built from source, with Node.js 22+ required. Its model registry covers local Ollama and LM Studio runtimes alongside cloud providers including OpenAI, Anthropic, Gemini, Groq, DeepSeek, and OpenRouter. Documented work includes reading and analyzing a CSV, plotting results, selecting models, configuring BYOK credentials, and searching the web. Its extension loader accepts Slack marketplace extensions, Claude-style manifests, OpenAgent manifests, and .mcp.json files. Execution stays in the user's terminal and workspace; local models need no key, while cloud models and some search backends require network access and provider credentials.

A user submits a natural-language task through openagent or npm start. OpenAgent plans the task, invokes tools, and delivers output in the terminal; the documented example reads sales.csv, analyzes customer data, and plots the top ten customers. Models are selected with -m, --model or --provider, while --free rotates through a free or inexpensive catalog with fallback and --models prints the registry. --byok and the in-session /byok [provider key] command save cloud credentials to .env, while /models exposes model selection during a session. google_web_search chooses a backend from available credentials, falling back without a key from hosted Exa MCP to DuckDuckGo; Brave, Tavily, Serper, and Gemini are also configurable. Extension installation reads .claude-plugin/plugin.json, open-agent-extension.json, or .mcp.json, including MCP server declarations from a sibling .mcp.json file.

  1. A data practitioner who wants to inspect a local CSV and produce a chart from a terminal prompt.
  2. A developer already running Ollama or LM Studio who wants an agent without cloud credentials.
  3. A team that needs to switch among OpenAI, Anthropic, Gemini, Groq, DeepSeek, OpenRouter, and local models.
  4. An individual who wants free or inexpensive model rotation with automatic fallback when a model fails.
  5. A researcher who needs terminal-based web search with backend selection based on the active model and available keys.
  6. An advanced user extending terminal workflows through Claude-style manifests, OpenAgent manifests, or MCP configuration.

Key setup facts

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

Install / run
  • npm install -g @haseeb_heaven/open-agent
  • npm install && npm run build
Environment variables
OPENAI_API_KEY ANTHROPIC_API_KEY GEMINI_API_KEY OPENROUTER_API_KEY
Config files
.env.example .env
Runtime
Node.js 22+

How do you install or deploy this agent?

Node.js 22+ is required. The shortest installation path is the published npm package:

npm install -g @haseeb_heaven/open-agent
openagent

Ollama and LM Studio require no API key. For cloud models, copy .env.example to .env and set the applicable variable, such as OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, or OPENROUTER_API_KEY; BYOK setup is also available inside the program.

To build the documented latest multi-provider work from source, check out the feature branch:

git clone --branch feature https://github.com/haseeb-heaven/open-agent.git
cd open-agent
npm install && npm run build
npm start

How do you use this agent?

Start in local-first mode; Ollama is used when it is running:

npm start

Analyze a CSV using the free or inexpensive catalog with automatic fallback:

npm start -- --free "analyze this CSV"

List models or configure provider keys interactively:

npm start -- --models
npm start -- --byok

A model or provider can also be selected explicitly:

npm start -- -m openrouter-free
npm start -- -m ollama/llama3.1:8b
npm start -- --provider groq -m llama-3.1-8b-instant

The complete source-based example is:

npm install && npm run build
npm start -- --free "analyze sales.csv and plot top 10 customers"

During a session, use /models, /byok [provider key], and /websearch. Tool auto-approval is intended only for trusted workspaces:

npm start -- -y

What are this agent's strengths and limitations?

Pros
  • It combines keyless Ollama and LM Studio operation with a broad set of cloud model providers, reducing provider lock-in.
  • --free supplies free or inexpensive model rotation and fallback without requiring an OpenAgent account.
  • Web search includes a no-key Exa-to-DuckDuckGo fallback and optional Brave, Tavily, Serper, and Gemini backends.
  • The extension loader understands Claude-style manifests, OpenAgent manifests, and .mcp.json declarations.
  • The CLI explicitly supports Windows, macOS, and Linux and has a one-command global npm installation path.
Limitations
  • Node.js 22+ is mandatory, excluding environments pinned to older Node.js releases.
  • The README places the latest multi-provider work on the feature branch, creating a stability and upgrade consideration for adopters.
  • Ollama and LM Studio must be operated separately, while each cloud provider requires its own credentials.
  • There is no documented importable library, desktop application, or self-hosted web-service mode; the primary interface is the terminal.
  • --yolo and extension Auto mode bypass tool or workspace-trust prompts and are suitable only for trusted workspaces.

How does this agent compare with similar options?

OpenAgent is based on Google's Gemini CLI and modified by Haseeb Mir as the open-agent fork. In contrast to the single Gemini entry point suggested by its upstream origin, this repository explicitly documents paths for Ollama, LM Studio, OpenAI, Anthropic, Gemini, Groq, DeepSeek, OpenRouter, and other providers. The supplied material does not include comparative performance or feature benchmarks.

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

Agent Source review Form / cost Stars Updated Language Full support on
OpenAgent Terminal Agent This agent 50 · Major gaps CLIFree ★ 279 8d ago TypeScript OpenAI API · Claude API
Mysti AI Coding Team 81 · Good IDE extensionFree + model costs ★ 1.2k 11d ago TypeScript Codex · Claude Code · OpenAI API · Claude API
AgenC Core 76 · Good CLIFree + model costs ★ 144 1d ago TypeScript —
Codewhale Terminal Coding Agent 79 · Good CLIFree + model costs ★ 41k today Rust OpenAI API · Claude API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
50/ 100 5-point scale 2.5 / 5
Trust 12/29
Reliability 8/14
Adaptability 9/18
Convention 10/18
Effectiveness 7/13
Verifiability 4/8
Why each dimension lost points
Trust12 / 29 · 2.1/5

Documentation describes approval prompts by default, read-only Plan mode, YOLO as approving all actions including dangerous ones, and per-run approval for sandbox expansion. This supports partial permission controls. Deductions: the CLI also exposes --yolo, extension auto-approval, and writable workspace access, while the supplied code does not show that every high-impact tool shares the same controls. The docs cover cloud keys and search configuration but do not fully explain prompt, file-content, and telemetry flows or retention; the sample does not show key protection implementation, external-action auditing, or clear rollback guarantees.

Reliability8 / 14 · 2.9/5

The entry point provides readable handling for startup failures, cleanup timeouts, and API errors, and the package and installation docs specify dependencies and the Node.js requirement. Deductions: README, package metadata, and docs mix Gemini CLI, open-agent, and OpenAgent names; the README's global package name also differs from package metadata. The supplied material does not establish availability guarantees for all providers, optional dependencies, or fallback paths.

Adaptability9 / 18 · 2.5/5

The README and installation docs address terminal users and contributors, covering local models, cloud BYOK, multiple operating systems, and interactive and headless use. Deductions: although models, search backends, and approval options are listed, the material does not define the agent's complete boundaries for files, network, shell, and extensions. Sample skill triggers are local in scope, and one asks for a particular subagent, so they do not establish consistent product-wide triggering rules.

Convention10 / 18 · 2.8/5

The repository includes a documentation index, installation and quickstart guides, configuration and error references, command examples, and an Apache-2.0 license. Deductions: sandbox documentation uses several legacy product and package names, and uninstall guidance mentions other distribution methods. The supplied material does not establish a clearly accountable maintainer or provide enough release and change history; limitations are documented only in some sections.

Effectiveness7 / 13 · 2.7/5

The product is presented as a terminal agent that plans from natural-language tasks, uses tools, and supports local or cloud models. The README gives concrete examples such as CSV analysis, and output can be text or JSON. Deductions: the materials do not provide reviewable evidence of task quality, success rates, cost, or resource use; although local models support offline use, the documented comfortable configuration requires substantial memory.

Verifiability4 / 8 · 2.5/5

README claims about installation, models, keys, and tests can be traced to supporting docs, package configuration, and entry-point code; test scripts are listed. Deductions: commands and sample tests show that test materials exist, not that they passed. Product names, package names, and inheritance descriptions conflict across files. The supplied source does not directly corroborate several major README safety and capability claims, and the boundary between inference and verified fact is not consistently marked.

Risks and how to mitigate them
  • Before using shell commands, file edits, extension installation, or cloud models, check the active approval mode and sandbox settings; --yolo and extension auto-approval reduce interactive confirmation.
  • Product and package names differ across the supplied docs; verify commands for the chosen distribution before installing or uninstalling.
  • This assessment is based only on the supplied static material; no execution, tests, or dependency security checks were performed.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision 9780412432f6 New commits since this review; the score may not cover them
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/open-agent.svg)](https://followagents.com/en/agents/open-agent)
<a href="https://followagents.com/en/agents/open-agent"><img src="https://followagents.com/badge/open-agent.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. v4.1.4 OpenAgent v4.1.4 — Bundle version metadata fix
    Release notes excerpt
    OpenAgent v4.1.4 This patch release fixes stale CLI version metadata in the published bundle. Fixed - Rebuilt core generated version metadata before bundling. - Rebuilt the npm bundle from a clean output directory. - Verified that the bundled executable and telemetry metadata report 4.1.4. Installation ```bash npm install -g @haseeb_heaven/[email protected] ```
    View on GitHub ↗
  2. v4.1.3 OpenAgent v4.1.3 — Fast provider failover
    Release notes excerpt
    OpenAgent v4.1.3 This release improves response latency for explicit model selections and makes free-provider failover bounded and observable. Performance - Explicit Gemini model selections bypass the auto-model classifier on fresh turns, while model changes during an active sequence retain re-routing. - OPENAGENT_CLI_FAST_MODE=1 caps compatible-provider completions at 1024 tokens, skips the optional next-speaker follow-up, bounds provider requests to 3 seconds, and limits fast failover to one alternate candidate. …
    View on GitHub ↗
  3. v4.1.1 v4.1.1 — Free-model picker, extensions market & post-release fixes
    Release notes excerpt
    Ships the develop-branch feature set previously (mis-)tagged as an unreleased v4.1.0, renumbered to avoid colliding with main's already-released v4.1.0 (provider crash / test-isolation fixes — see that release). Features (from the develop v4.1.0 feature set) - feat(cli): /free-models interactive picker for free-tier models, plus /free shortcut - feat(cli): /extensions market — browse and install extensions from the registry Bugfixes (this release) …
    View on GitHub ↗

FAQ

Do I have to pay for a model API?
No. Ollama and LM Studio work without keys, and --free provides a free or inexpensive model catalog. Paid cloud-provider charges apply only when those services are selected.
What local resources can it access?
It uses tools from the terminal and workspace. The documented example reads sales.csv, analyzes it, and creates a plot; extension installation and .env credential storage also use the filesystem.
Does web search work without an API key?
Yes. The documented no-key chain tries hosted Exa MCP and then DuckDuckGo. Other backends can be enabled with their respective environment variables.
Which operating systems and runtime are supported?
Windows, macOS, and Linux are explicitly listed, with Node.js 22+ required.
What is the risk of automatic approval?
-y, --yolo automatically approves tools, and extension Auto mode automatically grants workspace trust. The documentation limits these modes to trusted workspaces.
Is OpenAgent Terminal Agent open source?
Yes. The source code is on GitHub (haseeb-heaven/open-agent) under the Apache-2.0 licence.
Is OpenAgent Terminal Agent safe to use?
FollowAgents' FARS review (Nov 08, 2026) scored OpenAgent Terminal Agent 12/29 on trust and safety. None of the eight safety controls the review checks for was missing outright. The repository has changed since that review.
Is OpenAgent Terminal Agent still maintained?
Yes. The latest commit on GitHub is from 2026-11-12, within the last 30 days. The latest release is v4.1.4 (2026-07-31).
Who makes OpenAgent Terminal Agent?
OpenAgent Terminal Agent is published on GitHub by the account haseeb-heaven. FollowAgents has not verified which person or company is behind that account.
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