A current review of AI Agent Store as a directory, hosted-agent platform, starter-kit catalog, agency marketplace, and agent-task service, with security and procurement checks.
O
AI Tool Profile
Open Interpreter
Open Interpreter is an open-source terminal agent, forked from Codex, that reads and edits files and runs commands inside an OS-level sandbox with approvals. It is free under Apache 2.0 and works with local models through Ollama or LM Studio.
Description of Open Interpreter
Open Interpreter is an open-source agent that lives in your terminal. You open a project, type interpreter, and it can read files, edit code and run commands, asking before it goes beyond the current sandbox. The relaunched project is a fork of OpenAI's Codex command-line tool, so it keeps that terminal interface and inherits AGENTS.md instructions, skills, MCP servers and project configuration, while staying independent of any one model provider. It ships model-specific harnesses tuned for low-cost and open-weight models such as Kimi, Qwen and DeepSeek.
Work runs inside an OS-level sandbox on macOS, Linux and Windows. Reads, writes and network access are gated, network starts disabled in permission profiles unless you enable it, and anything outside the workspace needs explicit approval, with profiles for read-only, workspace-write or full access. Built-in providers include OpenAI, Amazon Bedrock, Ollama and LM Studio, and the provider catalog adds Anthropic, OpenRouter, DeepSeek, Moonshot, Z.ai, Alibaba Qwen, Groq and others, plus any OpenAI-compatible or Anthropic-compatible endpoint. You can run several sessions at once and resume or fork them.
On privacy, the site says local models stay on your machine and requests made with your own API key go directly to that provider, but requests to hosted models offered through Open Interpreter pass through its servers and are logged for up to 30 days. A separate desktop app brings the same workflow to Word, Excel, PDFs, browsers and local files for people who do not use a terminal.
Features of Open Interpreter
- Terminal agent that reads files, edits code and runs commands inside an OS-level sandbox with per-action approvals.
- Works with local models through Ollama or LM Studio, or with hosted providers including OpenAI, Anthropic, DeepSeek and Kimi.
- Supports AGENTS.md instructions, skills and MCP servers, and runs multiple sessions that can be resumed or forked.
Frequently asked questions
Is Open Interpreter free?
Yes. It is open source under the Apache 2.0 license. If you use a hosted model you pay that provider, or Open Interpreter's hosted option, for the model usage.
Does Open Interpreter keep my code private?
Local models stay on your machine, and your own API key sends requests straight to that provider. Hosted models offered through Open Interpreter route requests through its servers, where they are logged for up to 30 days.
Website: https://www.openinterpreter.com/
Company: Open Interpreter
Key facts
Open-source terminal agent forked from Codex, with an OS-level sandbox and approvals; runs on local or hosted models. Terminal-first, not a general desktop GUI agent. Free under Apache 2.0.
| Pricing model | Open source |
|---|---|
| Free tier | Yes · Apache 2.0 open-source CLI; model usage billed by your chosen provider |
| Starting price | Not verified |
| Data residency | Not verified |
| Compliance (as stated by vendor) | Not verified |
| Integrations | Ollama, LM Studio, OpenAI, Amazon Bedrock, Anthropic, OpenRouter, DeepSeek, Groq |
| Public API | Not verified |
| Self-hostable | Yes |
| Official site | Not verified |
| Can a general AI assistant replace it? | A chatbot can suggest commands but cannot run them. Open Interpreter executes them in a sandbox; with a local model nothing leaves your computer. |
| Last verified | 2026-10-12 by editor |
Alternatives & Similar Tools
A
AnythingLLM Open Source
AnythingLLM is a free, MIT-licensed AI assistant that runs on your own computer, with document chat, agent skills, background jobs and an on-device meeting assistant. It needs no account or API key, and it can be self-hosted for teams.
T
Together AI Paid
Together AI is a cloud platform for running open models through a per-token serverless API, plus dedicated endpoints, GPU clusters and fine-tuning. Hosted GLM-5.3-Flash, for example, is listed at $0.15 input and $0.50 output per million tokens.
K
Kimi (Moonshot AI) Paid
Kimi is Moonshot AI's assistant and model family, offered as the kimi.com agent workspace and as a pay-as-you-go API. The Kimi K2.7 Code model is listed at $0.95 input and $4.00 output per million tokens.
Z
Z.ai (GLM) Paid
Z.ai offers the GLM model family through a chat app and a developer API billed per million tokens. GLM-5.3-Flash is listed at $0.15 input and $0.50 output, and the API is compatible with the OpenAI SDK.
G
Gemini API (Google AI Studio) Freemium
The Gemini API and Google AI Studio let developers build with Google's Gemini models for text, code, images, video and speech. A free tier covers some models; paid use is billed per million tokens, such as $0.30 in and $2.50 out on Gemini 3.5 Flash-Lite.
Update history
- 2026-10-12 · ai alternative note updated (editor)
- 2026-10-12 · editor verdict updated (editor)
- 2026-10-12 · self hostable updated (editor)
- 2026-10-12 · integrations updated (editor)
- 2026-10-12 · pricing page url updated (editor)
- 2026-10-12 · free tier updated (editor)
- 2026-10-12 · pricing model updated (editor)
Beyond the tool
Need the outcome rather than the software?