Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

Oh My Pi by Stencil Labs (Can Bölük)

Open-source terminal coding agent (`omp`), built by Stencil Labs as a fork of the Pi coding agent by Mario Zechner, with a native Rust core, IDE-style tooling and Windows-native support.

Terminal coding agents Terminal agentOpen source · MITFree to start

Use it in: CLI IDE Works with: MCP Local models Own API key Multi-agent Headless / CI

Price
Free (OSS)
free and open source
Popularity
#8 in Terminal
Gid Score 54 / 100 · #28 of 255 ranked AI agents
Trend
Growing
downloads up 18.8% over 30 days · up 16.4% last week
Development
Actively updated
latest 19.0.1, 2d ago
Community
39.6K GitHub stars
311K package downloads a week

Usage data: latest readings Nov 19 to Nov 21, 2026, last checked Nov 21, 06:32 UTC. Date of each number

What Oh My Pi does

Oh My Pi is a terminal agent from Stencil Labs, first released in January 2026. You use it through a command-line tool and IDE (Zed via ACP) on macOS, Linux and Windows. Its documentation covers MCP servers, subagents or parallel agents, a non-interactive mode for scripts and CI, your own API key and local models. It can run models from Anthropic, OpenAI, Google, xAI, Mistral and DeepSeek and others. It is free and open source (MIT); you pay only for the models it calls.

Key facts

MakerStencil Labs (Can Bölük)
TypeTerminal agent
First releasedJanuary 2026
LicenseMIT
InterfacesCLI, IDE (Zed via ACP)
PlatformsmacOS, Linux, Windows
Main languageTypeScript
Open issues and PRs5,077

Pricing

MIT-licensed open-source CLI; no pricing page found on omp.sh (checked 2026-10-05).

Checked Nov 4, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT)
  • Runs onmacOS, Linux, Windows
  • Where you use itCLI, IDE (Zed via ACP)
  • Supports MCP?Yes
  • Model providersanthropic, openai, google, xai, mistral, deepseek, moonshot, qwen, amazon, openrouter, any OpenAI-compatible, local
  • Subagents / multi-agent?Yes
  • Runs in scripts / CI?Yes
  • Feature comparisonAll agents
  • Closest alternativeClaude Code · all alternatives

What's new in Oh My Pi: November 2026 so far

Full monthly summary

November brought major provider and model additions, improved conversation handling for several platforms, and numerous reliability fixes across authentication, reasoning, and tool execution. The month saw support for Liquid AI, Otari, Modular Cloud, and Antigravity CLI alongside significant improvements to Gemini, Claude, and OpenAI-compatible model support.

Action needed: Removed PI_TOKENIZER_ACCURATE environment variable; all models now counted with native tokenizer.
  • Added support for Liquid AI decision models and Google Decisions API for judgment tasks.
  • Introduced Antigravity CLI provider with managed installation and native thinking controls for Gemini, Claude, and GPT models.
  • Improved Gemini 4 response handling across multiple platforms to support long outputs that exceed single segments.
  • Added opt-in standard Responses WebSockets for incremental turns with automatic HTTP/SSE fallback.

18 releases this month · summarised from the official release notes · all months

AgentGid articles about Oh My Pi

All guides

Get started with Oh My Pi

npmnpm install -g @oh-my-pi/pi-coding-agent

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

What Oh My Pi users report right now

All 8 reports, questions and fixes →

Open Request Users ask for a fullscreen mode like Pi's, where the input box and footer stay docked at the bottom while the transcript scrolls; today long sessions push the prompt off screen unless a third-party extension is installed.

Reported on GitHub · 24 👍

Open Request Users ask to keep several live sessions inside one omp process and switch between them; today switching with /resume or /new replaces the running session, so parallel work needs separate terminals.

Reported on GitHub · 12 👍

Open Users report that DeepSeek V4 Flash kept damaging files through omp's edit tool, deleting code and then retrying with more broken edits. The issue is still open; one reporter says it stopped on 18.1.10, after the edit engine was rewritten.

Reported on GitHub · 11 👍

Open Users report that Google suspended Antigravity on their accounts with a TOS_VIOLATION error after they signed in to it through omp. The project marked the issue wontfix, and release 18.18.4 paused the Google Antigravity provider.

Reported on GitHub · 9 👍

Open Request Users ask for the old blocking wait tool back: since 18.17.0, wait returns after short fixed intervals while background jobs run, and users report that models then call it again and again, spending extra tokens.

Reported on GitHub · 8 👍

How do I point omp at a self-hosted OpenAI-compatible endpoint?

Add a custom provider under providers: in ~/.omp/agent/models.yml with your endpoint as baseUrl, api: openai-completions, an apiKey (an environment variable name or the key itself) and the list of models. The provider then appears next to the built-in ones and its models are selected as provider/model; a local server that needs no key can use auth: none.

Source · Where it was asked

The most discussed problems in its GitHub repository, checked Nov 17, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.

Add-ons for Oh My Pi: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for Oh My Pi. Savings and results depend on your workload.

Compare Oh My Pi with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
1
Claude CodeAnthropic
89 21.7M up 25.9% up 18.1% 156K+142/day 2.1.330yesterday $20/mo
2 84 27.5M up 4.1% up 6.5% 136K+131/day 0.168.08d ago Free + $8/mo
3
OpenCodeAnomaly (SST team)
80 3.9M up 10.4% up 24.2% 228K+254/day 2.3.23d ago Free + $10/mo
7
PiEarendil Inc. (created by Mario Zechner)
72 6.6M up 4.1% up 33.1% 123K+182/day 1.6.0yesterday Free (OSS)
15 63 522K up 19.0% up 7.1% 109K+35/day 0.70.02d ago API usage or license
20
ClineCline Bot Inc.
58 82K down 3.3% up 9.8% 71.8K+33/day 4.1.27today Free + $9.99/mo

Ratings from people who use Oh My Pi

No ratings yet. Used Oh My Pi? Rate it and say what it is good and bad at.

Oh My Pi news

All AI agent news

  1. Release GitHub Releases

    Oh My Pi 19.0.1 released

    Fixed GIF images failing Liquid AI judgments with HTTP 422; they are now sent as PNG; Anthropic strict-tool fallback now treats a Vertex org-policy rejection of structured_outputs (allowedPartnerModelFeatures / "disallowed feature structured_outputs") as a…

  2. Release GitHub Releases

    Oh My Pi 18.22.2 released

    Added the native Kiro provider: sign in with AWS IAM Identity Center, AWS Builder ID, Google, GitHub, or a Kiro API key (KIRO_API_KEY), stream responses with reasoning, tool calls, and images, and…; Added a definitive option to OAuthError…

  3. Data AgentGid data

    Oh My Pi downloads up 29% in a week

    285K npm downloads in the 7 days to Nov 14, against 221K the week before.

What changed: recent Oh My Pi releases

Monthly summary · Full changelog

19.0.1
  • Fixed GIF images failing Liquid AI judgments with HTTP 422; they are now sent as PNG
  • Anthropic strict-tool fallback now treats a Vertex org-policy rejection of structured_outputs (allowedPartnerModelFeatures / "disallowed feature structured_outputs") as a strict-tools rejection…
  • Kiro requests rejected with Input is too long. or CONTENT_LENGTH_EXCEEDS_THRESHOLD can now recover through conversation compaction
  • Kiro thinking off now turns reasoning off instead of running the model's default effort; models that cannot disable reasoning use their lowest effort
  • Kiro /usage shows purchased add-on credits, and an account whose plan credits are spent keeps serving while add-on credits remain
  • Kiro Identity Center logins in AWS GovCloud (US) now list profiles in us-gov-west-1 and us-gov-east-1 instead of the commercial regions, which reject GovCloud tokens
19.0.0
  • Added support for excluding custom messages from model context and compaction or branch summaries, while allowing queued steering and follow-up messages to continue correctly after excluded messages.
  • Added a prewarm stream option for Anthropic Messages requests to refresh prompt caches without generating billable output.
  • Claude usage reports now include the account subscription plan in metadata.subscriptionPlan, supporting Max 5x, Max 20x, Pro, Team, and Enterprise plans.
  • Added retryUnreachableBroker and onBrokerRetry options to discoverAuthStorage, allowing hosts to control startup retries for temporarily unavailable authentication brokers and display retry status.
  • Fixed Claude account failover after a shared weekly usage limit recovers, ensuring accounts become available again when usage reporting no longer shows that window.
  • Authentication broker startup now tolerates temporary broker restarts and connection interruptions by retrying for up to 30 seconds, while still failing immediately for rejected tokens or…
Earlier releases
18.22.2
  • Added the native Kiro provider: sign in with AWS IAM Identity Center, AWS Builder ID, Google, GitHub, or a Kiro API key (KIRO_API_KEY), stream responses with reasoning, tool calls, and images, and…
  • Added a definitive option to OAuthError; isDefinitiveOAuthFailure now takes the error object and disables a credential marked definitive without matching its message
  • buildAnthropicSearchHeaders takes extraBetas, request-specific betas sent beside the web search beta
  • Added omitDemotedReasoning to StreamOptions: an Anthropic request leaves out other models' reasoning that it would otherwise replay as text, and a refused request reports how many such blocks it…
  • Fixed shutting down or cancelling an omp session making every other session sharing the agent directory see its OAuth accounts as depleted for 5 minutes.
  • OAuth accounts refreshed through an auth broker keep their stored routing metadata (such as an API endpoint) in the key built for the request, instead of losing it after the first refresh
18.22.1
  • A model on an extension's custom api can take the Anthropic on-demand compaction lane by declaring remoteCompaction: { api: "anthropic-messages", enabled: true }.
  • Fixed provider-error handling so failed tool calls are no longer fed back to the model as refusal explanations.
  • Fixed one-shot retries and title generation for custom Zhipu Coding Plan providers so Beijing-time quota resets are honored.
  • Fixed OpenAI remote compaction (V1 and V2) dropping configured headers of models.yml and extension-registered models, so header-authenticated gateways returned 401
  • Added support for request-specific Anthropic beta headers through the extraBetas option in buildAnthropicSearchHeaders.
  • Added omitDemotedReasoning to StreamOptions, allowing Anthropic requests to omit other models' reasoning that would otherwise be replayed as text.
18.22.0
  • Fixed slow streaming of Gemma tool calls with large arguments.
  • Moved binary analysis from the standalone ida and ghidra tools into the backend-neutral dsm namespace (xd://eval/dsm).
  • Replaced the ida.enabled, ida.maxOpen, and ida.idleCloseSec settings with disassembler.backend, disassembler.maxOpen, and disassembler.idleCloseSec.
  • Added Tern plan review editing and comments: double-click plans to edit them, select text to add Google Docs-style comments, and send comments to Refine.
  • Added Ghidra support with automatic setup of Ghidra, JDK, and PyGhidra when analysis is explicitly requested; Auto mode uses an installed IDA Pro when available and otherwise falls back to Ghidra.
  • Added support for sharing live analysis databases with child agents through db.handle() and dsm.open(handle).
18.21.0
  • Added automatic detection of thinking capabilities for previously unknown models, with persistent results and support for alternate effort and token-budget request formats.
  • Added Modal as a hosted inference provider.
  • Changed the local speech model from Kokoro to Phonon 31M.
  • Improved reasoning capability detection by preserving unverified thinking-level support and using endpoint-specific probe results when available.
  • Fixed xAI Grok OAuth model grok-composer-2.5-fast being incorrectly identified as non-reasoning; it now supports thinking levels from minimal through xhigh.
  • Updated the AgentSession run lifecycle API: agent_end is emitted once when a run can no longer resume, and agent_pause reports runs that stop while awaiting work.

Oh My Pi prices over time

Token prices of Anthropic modelsnewest Anthropic model in each family, output price per 1M tokens
Anthropic OpusAnthropic SonnetAnthropic Haiku

Oh My Pi popularity and usage data

Oh My Pi was downloaded 311K times from npm in the week ending Nov 19, 2026, up 16.4% on the week before and up 18.8% over the last 30 days compared with the 30 before. The GitHub repository has 39.6K stars, 3,579 of them added in the last 30 days. The latest stable release is 19.0.1, published Nov 19, 2026; there were 31 stable releases in the past 30 days. It was mentioned in 44 Hacker News posts and comments over the last 30 days.

Downloads per daynpm, 7-day average 44.4K/day
GitHub starsrunning total 39.6K
Hacker News mentionsposts and comments, rolling 7-day total 7 this week
Website rankTranco list; a lower rank means more traffic #301,962

Download the raw daily series: oh-my-pi.csv

Gid Score breakdown

Adoption56
Community67
Attention34
Momentum59

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 19, 2026Nov 21, 06:22 UTC
GitHub starsNov 21, 2026Nov 21, 06:26 UTC
Website rank (Tranco)Nov 20, 2026Nov 21, 06:32 UTC
Hacker News mentionsNov 20, 2026Nov 21, 06:27 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Oh My Pi FAQ

How much does Oh My Pi cost?

MIT-licensed open-source CLI; no pricing page found on omp.sh (checked 2026-10-05).

Is Oh My Pi open source?

Yes. Oh My Pi is open source, released under the MIT license.

How popular is Oh My Pi?

Oh My Pi was downloaded 311K times from npm in the week ending Nov 19, 2026, up 16.4% on the week before and up 18.8% over the last 30 days compared with the 30 before. The GitHub repository has 39.6K stars, 3,579 of them added in the last 30 days. The latest stable release is 19.0.1, published Nov 19, 2026; there were 31 stable releases in the past 30 days.

What is the latest version of Oh My Pi?

The latest stable release we track is 19.0.1, published on Nov 19, 2026.

What are the alternatives to Oh My Pi?

The closest alternatives in the same category by Gid Score are Claude Code, OpenAI Codex, OpenCode, Pi.

For the makers of Oh My Pi badges, corrections

Add a live badge to your README or site:

AgentGid: #8 in Terminal Gid Score: 54/100 downloads: 311K/week ▲19% 30d

[![AgentGid: #8 in Terminal](https://agentgid.com/badges/oh-my-pi-rank.svg)](https://agentgid.com/agents/oh-my-pi/)
[![Gid Score: 54/100](https://agentgid.com/badges/oh-my-pi-score.svg)](https://agentgid.com/agents/oh-my-pi/)
[![downloads: 311K/week ▲19% 30d](https://agentgid.com/badges/oh-my-pi-downloads.svg)](https://agentgid.com/agents/oh-my-pi/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: @oh-my-pi/pi-coding-agent. GitHub: can1357/oh-my-pi. Site rank: omp.sh on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: omp.sh, github.com, registry.npmjs.org, en.wikipedia.org.