Build full applications in the terminal with an AI agent
Combine models such as Qwen with the agent to write and iterate on code step by step
Best for：Independent developers
Coding / Developer
omp
omp is an open-source terminal coding agent that supports more than 60 model providers and can switch models during a session.
Product type: CLI Coding AgentPricing: UnknownAPIMaster integration: Unknown
Website created
2026-05-11
OpenRouter token usage rank
#7
Source: OpenRouter
Monthly unique visitors
187,532
Source: SimilarWeb
Overview
omp is positioned as a command-line agent tool for developers to use in local projects, running through a TUI or GUI interface. After starting it in a project directory, users can have the agent perform CLI operations and call different models to handle tasks. Its core strengths are support for switching models mid-session and local configuration, avoiding the limits of a single model. It is well suited to developers who need flexible model routing and work with real codebases, with more emphasis on local persistence and multi-model switching than cloud-based shared agents or fixed-model tools.
One-line summary
omp is an open-source terminal coding agent that supports more than 60 model providers and can switch models during a session.
What people use it for
After the user starts omp in the terminal, they can have the agent use the CLI to complete AWS/GCP operations or code changes; when they hit model limits, they can enter /switch to move to another model and continue the task.
Best for
Developers and technical teams
How it works
Run the CLI in the project directory, configure the model provider and endpoint, then approve or inspect the Agent's actions in the terminal.
Quick facts
Product type
CLI Coding Agent
Pricing
Unknown
Please verify the current project pricing and model usage rules in the official repository.
APIMaster integration
Unknown
To be verified
Data confidence
Low
Last verified: 2026-08-29
Supported models / APIs
Provider configuration depends on the versionCustom endpoint support: to be verified
Core features and differentiators
Native LSP integration
Directly provides semantic rename, reference lookup, and diagnostics inside the terminal
Full DAP debugger
An in-process debugger that supports setting breakpoints, inspecting variables, and stepping through execution
Hashline content-hash editing
A code modification mechanism based on content hashes
Persistent IPython kernel
Preserves the state of imports, variables, and open files across sessions and sub-agents
Browser automation
Built-in browser operation capabilities
Support for multiple model providers
Use the same toolset to call different models through interfaces such as TUI, -p, RPC, and ACP
What is omp best for?
Debug Python programs in an IDE-integrated environment
Use the native DAP debugger to set breakpoints and inspect variables
Best for：Python developers
Incrementally build state like a Jupyter notebook
Use the persistent kernel to accumulate variable and file state step by step for iterative development
Best for：Data scientists and script developers
Run automation tasks with browser interaction
Have the agent operate the browser directly to complete web-related actions
Best for：Full-stack developers
Third-party key setup for omp (APIMaster integration)
We do not yet have reliable evidence that this product supports third-party keys, proxies, custom providers, or a custom base URL, so we do not show speculative setup steps or config values.
Community discussion
Discussion summary
Users generally understand omp as an AI coding agent tool with integrated IDE capabilities, emphasizing persistent state management and model routing for local development and agent workflows. Discussion focuses on comparisons with other agent tools, especially around memory persistence, orchestration reliability, and real delivery capability. Users also pay attention to how model routing is applied across different tasks and how integration works with specific providers.
Most discussed topics
- 1
How the persistent IPython kernel supports agents in incrementally building state
Users discuss how this design lets variables, imports, and files persist across sessions, enabling step-by-step iteration like a Jupyter notebook instead of re-deriving everything each time.
- 2
The real effect of model routing across task types or difficulty levels
Users share how routing automatically selects models based on the task, and how that affects coding efficiency and cost.
- 3
Comparison with other agent tools such as Droid in memory and orchestration
Users compare omp's durable harness and shared agents, discussing which is better suited to real project delivery and feedback loops.
- 4
Integration and usage experience with providers such as Google
Users ask how to configure providers, details such as anti-gravity subscriptions, and omp's stability in production environments.
- 5
Overall reliability and suitable scenarios for omp as a local coding agent
Users discuss its advantages for personal app development and avoiding cloud limitations, as well as how it pairs with Claude or other models.
FAQ
What is omp?
It is a terminal-oriented Coding Agent project; for specific capabilities, refer to the current state of the repository.
Does it support APIMaster?
Currently unknown. Until confirmed by official documentation or real-world testing, this page will not claim support.
Can it modify local files?
That depends on the enabled tools and permissions, and each action should be checked before execution.
Similar agents
Sources：Official websiteGitHub
Last verified: 2026-08-29 · Report a correction