- Fixed native OpenAI context compaction for sessions containing many screenshots, preventing image-size estimates from incorrectly causing compaction requests to be rejected.
- Fixed compatibility with Command Code DeepSeek and other DeepSeek-family models by preserving the reasoning context required for warm OpenAI Responses sessions and correctly handling incomplete…
- Fixed waiting for subagent follow-up messages: responses now appear as background jobs that can be waited on or canceled, and are delivered only once.
- Improved /switch autocomplete so model and role suggestions use the same relevance ordering as the model picker, including support for @role aliases.
- Fixed concurrent skill:// searches blocking other filesystem operations and delaying subagent artifact publication.
- Fixed compatibility checks for browser relays from other OMP versions and added guidance for resolving stale connection-refused errors.
Oh My Pi by Stencil Labs (Can Bölük)
Pulse Score
56 / 100
Rank #26 of 157
Downloads, last 7 days
241K
up 11.4% vs previous week
Downloads, last 30 days
720K
up 53.9% vs previous 30 days
GitHub stars
34.4K
about +111 a day
Latest release
18.6.1
2d ago · 44 in 30 days
Price
Free (OSS)
checked Oct 5, 2026
Overview
Open-source terminal coding agent (`omp`), a variant of the Pi coding agent from Stencil Labs, with a native Rust core, IDE-style tooling and Windows-native support.
Oh My Pi was downloaded 241K times from npm in the week ending Oct 4, 2026, up 11.4% on the week before and up 53.9% over the last 30 days compared with the 30 before. The GitHub repository has 34.4K stars, 4,890 of them added in the last 30 days. The latest stable release is 18.6.1, published Oct 4, 2026; there were 44 stable releases in the past 30 days. It was mentioned in 58 Hacker News posts and comments over the last 30 days.
Oh My Pi usage and attention over time
Download the raw daily series: oh-my-pi.csv
Install Oh My Pi
| npm | npm 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.
Key facts
| Maker | Stencil Labs (Can Bölük) |
|---|---|
| Type | Terminal agent |
| First released | January 2026 |
| License | MIT |
| Interfaces | CLI |
| Platforms | macOS, Linux, Windows |
| Main language | TypeScript |
| Open issues and PRs | 3,445 |
Pricing
MIT-licensed open-source CLI; no pricing page found on omp.sh (checked 2026-10-05).
, checked Oct 5, 2026. Prices change often; confirm before you buy.
Pulse Score breakdown
Adoption53
Community64
Attention38
Momentum77
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
What changed: recent Oh My Pi releases
- When a DeepSeek turn ends with raw <｜DSML｜…> tool-call text that could not be parsed into a real call, and no tool call was made, the broken markup is now removed from the message before it is…
- Fixed Antigravity chat and image requests sending an outdated client version when the model list came from cache, which could make newer models such as Claude Opus 5.5 unavailable.
- When a DeepSeek model writes a broken DSML tool call (for example with the opening <｜DSML｜toolcalls> and <｜DSML｜invoke> tags missing), its closing tags are now kept in the streamed text instead of…
- Fixed DeepSeek V4 model IDs and the V4.1 Flash alias lacking version information in model identity and dashboards (#14194).
- Fixed Antigravity models such as Claude Opus 5.5 and Sonnet 5.5 disappearing after omp models refresh. When the update check failed, omp reported an outdated Antigravity client version (2.8.0), so…
- DSML tool calls from DeepSeek models are now parsed on every host. This includes local servers (llama.cpp, LM Studio, vLLM), custom providers from models.yml, and gateways that weren't on the old…
- Added provider-reported usage cost, the unnormalized provider ID, and the requested model ID to CostEstimatorContext, allowing cost estimators to use the cost already recorded for a request…
- Improved tool-result supersession so path reads with selectors are tracked independently from bare-path reads, while failed results supersede only earlier failed results for the same key.
- Fixed parallel tool calls with reused or empty IDs executing with another call’s arguments or merging results; each call now executes and reports its own payload.
- Fixed completed tool calls being retried after a transient provider-stream read error; incomplete calls from the affected turn are now discarded.
- Fixed previously read code being removed from context when a subsequent read returned a summary, truncated content, or an error.
- Fixed intent tracing for tools that define i as a real argument, preserving the argument and its declared schema order.
- Fixed AWS credentialprocess on Windows stripping backslashes from unquoted paths such as C:\Users\me\helper.exe; commands are now split with Windows command-line rules there, matching the AWS CLI.
- Added closeModelCache() (@oh-my-pi/pi-catalog/model-cache) to release the shared default models.db handle so an agent directory can be deleted on Windows; the next cache access reopens it
- task.completionProbeMs is replaced by the on/off setting task.completionProbe; an existing task.completionProbeMs migrates automatically (0 → off, any period → on).
- SessionStorage.claimSessionFile(sessionPath) is replaced by claimSession(sessionId, sessionPath) (which also refuses when the path now holds a different session), and sessionOwnerLeasePath() by…
- /dump all writes a zip to the temp directory with the main transcript, the LLM request JSON, and one file per subagent transcript (nested subagents included, killed ones marked aborted); the TUI…
- Added /effort [level] to set the thinking level without switching models: bare /effort opens a picker, and completions offer only the current model's levels within the session effort ceiling. Its…
- Added createAuthGatewayRouter, the auth-gateway's routes without the HTTP listener, and serveAuthGatewayStdio, which serves them as JSON lines ({"id", "path", "body"} in, {"id", "status", "body"}…
- Added omp auth-gateway stdio: a long-lived inference server for other programs speaking JSON lines on stdin/stdout ({"id", "path": "/v1/chat/completions", "body"} in, {"id", "status", "body"} out)…
- Reduced CPU use while streaming with several agents active: extension messageupdate handlers are delivered through a lighter queue, and RPC no longer processes subagent events unless a client…
- Fixed web search stopping at Perplexity's anonymous signup wall instead of falling back to the next configured provider (#12756).
- Fixed imported Claude Code sessions on Windows reporting the encoded C--… directory name instead of the registered project path when the transcript records no cwd
- Fixed JavaScript eval wait()/handle.wait() ignoring a positional timeout; h.wait(30) now waits up to 30 seconds like { timeout: 30 }, and mixing an options object with positional arguments throws…
- Fixed lenient argument validation for tools such as yield: malformed tool-call JSON is now reported to the model instead of causing the tool to run with empty arguments.
- Fixed Cursor cached prompt token accounting to prevent duplicate input-token and cost reporting on cached turns.
- Fixed auth-broker credential handling so late token-refresh responses cannot restore logged-out credentials or overwrite a newer login.
- Fixed new Fireworks sessions failing on the first turn by updating the default model to kimi-k3, which is currently supported by Fireworks.
- Added goal management for RPC hosts and optional automatic goal continuation via goal.continuationModes: ["rpc"]. RPC clients can create, inspect, pause, resume, and remove goals, and view the…
- Added --goal <objective> for interactive launches to begin a new session in goal mode without requiring the /goal command.
Oh My Pi alternatives
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
OpenAI CodexOpenAI |
83 | 25.6M | up 5.7% | up 21.2% | 15.2M | 128K+153/day | 0.160.1yesterday | Free + $8/mo | ||
| 3 |
Claude CodeAnthropic |
80 | 14.8M | up 11.6% | down 36.4% | 27.1M | 150K+161/day | 2.1.290yesterday | $20/mo | ||
| 5 |
PiEarendil Inc. (created by Mario Zechner) |
75 | 5.2M | up 29.8% | up 52.1% | — | 113K+378/day | 1.0.4yesterday | Free (OSS) | ||
| 7 |
OpenCodeAnomaly (SST team) |
73 | 3.3M | up 22.0% | up 6.1% | 1.2M | 212K+200/day | 1.18.346d ago | Free + $10/mo | ||
| 24 |
Gemini CLIGoogle |
57 | 453K | up 4.7% | up 1.8% | 1.1M | 107K+24/day | 0.62.07d ago | Varies | ||
| 34 |
ClineCline Bot Inc. |
52 | 95K | up 10.1% | down 37.2% | 5.5M | 69.9K+63/day | 0.0.434d ago | Free + $9.99/mo | ||
| No agents match that filter. | |||||||||||
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 241K times from npm in the week ending Oct 4, 2026, up 11.4% on the week before and up 53.9% over the last 30 days compared with the 30 before. The GitHub repository has 34.4K stars, 4,890 of them added in the last 30 days. The latest stable release is 18.6.1, published Oct 4, 2026; there were 44 stable releases in the past 30 days.
What is the latest version of Oh My Pi?
The latest stable release we track is 18.6.1, published on Oct 4, 2026.
What are the alternatives to Oh My Pi?
The closest alternatives in the same category by Pulse Score are OpenAI Codex, Claude Code, Pi, OpenCode.
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.