OpenAgent Terminal Agent
Plan and execute terminal tasks with local, free, or bring-your-own-key models.
- Source repo
- haseeb-heaven/open-agent
- Stars
- ★ 279
- Last updated
- 8d ago
- License
- Apache-2.0
- Primary language
- TypeScript
- FA score
- 50/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- 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)
- Source review
- 50/100 · Major gaps
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.
- A data practitioner who wants to inspect a local CSV and produce a chart from a terminal prompt.
- A developer already running Ollama or LM Studio who wants an agent without cloud credentials.
- A team that needs to switch among OpenAI, Anthropic, Gemini, Groq, DeepSeek, OpenRouter, and local models.
- An individual who wants free or inexpensive model rotation with automatic fallback when a model fails.
- A researcher who needs terminal-based web search with backend selection based on the active model and available keys.
- 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-agentnpm install && npm run build
- Environment variables
OPENAI_API_KEYANTHROPIC_API_KEYGEMINI_API_KEYOPENROUTER_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
openagentOllama 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 startHow do you use this agent?
Start in local-first mode; Ollama is used when it is running:
npm startAnalyze 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 -- --byokA 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-instantThe 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 -- -yWhat are this agent's strengths and limitations?
- It combines keyless Ollama and LM Studio operation with a broad set of cloud model providers, reducing provider lock-in.
--freesupplies 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.jsondeclarations. - The CLI explicitly supports Windows, macOS, and Linux and has a one-command global npm installation path.
- Node.js 22+ is mandatory, excluding environments pinned to older Node.js releases.
- The README places the latest multi-provider work on the
featurebranch, 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.
--yoloand 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?
Why each dimension lost points
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.
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.
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.
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.
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.
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.
- 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.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
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 ↗ -
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 ↗ -
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?
--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?
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?
Which operating systems and runtime are supported?
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?
Is OpenAgent Terminal Agent safe to use?
Is OpenAgent Terminal Agent still maintained?
Who makes OpenAgent Terminal Agent?
Thanks — we use this to improve the page.