code-yeongyu/senpi
Snapshot of code-yeongyu/senpi: 391★, TypeScript, AI Tools. pi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. opinionated fork of badlogic/pi-mono with extension-first additions. ganbare ganbare senpi 頑張れ頑張れ先輩
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
Snapshot
Top contributors
Show top contributors
senpi
⚠️ Experimental. senpi is an opinionated, in-flight fork of badlogic/pi-mono. It powers Dori under the hood and reflects what one specific AI assistant needs from a coding-agent runtime. Use it; don't bet a production pipeline on it.
senpi is a senpai-name pun and a more sane pi with extra batteries included — a TypeScript monorepo that rebrands pi-mono's coding agent as senpi and ships a curated set of builtin extensions and core tweaks on top of upstream.
Upstream: pi-mono by @mariozechner — tools for building AI agents and managing LLM deployments.
Inspired by OMO, built as Dori's coding-agent runtime
senpi was born from two influences:
- Strong influence from OMO (oh-my-openagent). OMO is the heavyweight opencode harness with discipline agents (Sisyphus, Hephaestus, Prometheus), IntentGate, hash-anchored edits, Team Mode, skill-embedded MCPs, Ralph Loop, todo enforcers, and a lot more. senpi reuses many of OMO's signature ideas (intent gate, dynamic prompt, per-model presets, parallel-tool routing, todo continuation) but keeps the surface as light as possible so it can stay close to upstream pi-mono. Think of senpi as a light version of OMO that runs as a single pi CLI binary instead of an opencode plugin.
- senpi is the coding-agent runtime for Dori. Dori is Sisyphus Labs' AI assistant — see the Dori callout in OMO's README for context. senpi is usable standalone, but the design decisions (intent gate phrasing, builtin extension set, prompt presets per model family, branding) are tuned for what Dori needs when it executes code work.
Core source modifications are minimised and tracked in changes.md files alongside every modified subdirectory so upstream merge commits stay reviewable.
| Package | Description |
|---|---|
| @earendil-works/pi-telemetry | Vendor-neutral telemetry contracts, reference adapter, conformance tests, and typed schemas |
| @earendil-works/pi-ai | Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.) |
| @earendil-works/pi-agent-core | Agent runtime with tool calling and state management |
| @earendil-works/pi-coding-agent | Interactive coding agent CLI |
| @earendil-works/pi-tui | Terminal UI library with differential rendering |
Coming from OMO? Recommended extension setup
If you're migrating from OMO (oh-my-openagent), here is the practical map from "what I used in OMO" to "what to install in senpi". A lot of OMO's signature work is already wired into senpi as a builtin (nothing to install); the rest lives in the code-yeongyu/pi-* GitHub repos and is one senpi install away.
senpi is intentionally lighter than OMO — single CLI binary, not an opencode plugin. Some OMO concepts (Discipline Agents, Team Mode, Skills, Hashline, Ralph Loop,
/init-deep) have no 1:1 senpi counterpart and are flagged at the bottom of this section. If you need those, keep using OMO.
Already builtin in senpi — nothing to install
| OMO feature | senpi builtin |
|---|---|
| 🚪 IntentGate | Dynamic system prompt — every prompt opens with a forced intent gate before tool use. |
| ✅ Todo Enforcer | todowrite + continuation loop that re-engages idle agents. |
| Per-model tuning ("Model Setup") | prompt-preset — GPT-5.x / Claude Opus 4.{5,6,7} / Kimi K2.6 presets. |
| Session recovery / context management | compaction — adaptive thresholds, restoration tracker, emergency compaction, tool-result truncation. |
| Apply-patch on GPT models | gpt-apply-patch — Codex-style freeform apply_patch with Lark grammar. |
| Native web search (Anthropic + OpenAI) | anthropic-web-search, openai-web-search builtins. |
| Bash timeout discipline | bash-timeout — default + max-timeout enforcement, policy in system prompt. |
| Compaction-safe tool pairing | tool-pair-guard — strips orphan tool_result blocks. |
| Permission system (opencode-style allow/deny) | permission-system — rules, JSONL storage, TUI prompts, parser-aware patterns. |
Choose extensions for your OMO setup
Senpi builtins, standalone pi-* extensions, and the
OMO Senpi plugin
overlap. Do not install every standalone package when the capability is already provided by Senpi or the plugin.
| Capability | Senpi without the OMO plugin | Senpi with the OMO plugin |
|---|---|---|
| LSP | Install pi-lsp-client. | The plugin registers six LSP tools through its packaged daemon. Install pi-lsp-client only if you specifically need its /lsp inspector. |
| AST-grep | Install pi-ast-grep. | The plugin ships an AST-grep skill, helper, and installer scripts. pi-ast-grep remains optional when you want the native ast_grep_search and ast_grep_replace tools. |
| Comment checking | Install pi-comment-checker. | The plugin registers its own comment-checker component; do not install the standalone extension too. |
Rules and nested AGENTS.md | Already provided by the rules and nested-agents-md builtins. | Same; no standalone extension is required. |
| Web search and fetch | Already provided by the websearch and webfetch builtins. | Same; no standalone extension is required. |
| Persistent goals | Already provided by the goal builtin. | Same; no standalone extension is required. |
| Subagent profiles | pi-agent-system supports external launchers that set PI_AGENT_TYPE or SANEPI_AGENT_TYPE. | The plugin owns task/member routing and tool filtering, so pi-agent-system is normally unnecessary. Keep it only when another launcher relies on its environment-variable contract. |
For standalone Senpi without the OMO plugin, install only the non-builtin capabilities you need:
senpi install git:github.com/code-yeongyu/pi-lsp-client # 🛠️ LSP: rename / goto / refs / diagnostics + /lsp inspector
senpi install git:github.com/code-yeongyu/pi-ast-grep # 🛠️ AST-Grep across 25 languages (auto-downloads sg)
senpi install git:github.com/code-yeongyu/pi-comment-checker # 💬 Comment Checker — the standalone pi port of OMO's hook
# Optional — only if you used the matching OMO surface:
senpi install git:github.com/code-yeongyu/pi-cua-integration # 🖥️ Computer-use bindings (desktop / browser)
senpi install git:github.com/code-yeongyu/pi-anthropic-computer-use # Claude-native computer use
senpi install git:github.com/code-yeongyu/pi-anthropic-code-execution # Claude-native code execution
senpi install git:github.com/code-yeongyu/pi-google-code-execution # Google-native code execution
senpi install git:github.com/code-yeongyu/pi-openai-code-interpreter # OpenAI Code Interpreter
senpi install git:github.com/code-yeongyu/pi-anthropic-text-editor # Claude-native text editor tool
senpi install git:github.com/code-yeongyu/pi-anthropic-tool-search # Claude-native tool search
senpi install git:github.com/code-yeongyu/pi-anthropic-web-fetch # Claude-native web fetch
senpi install git:github.com/code-yeongyu/pi-google-google-search # Google Search grounding
senpi install git:github.com/code-yeongyu/pi-google-url-context # Google URL grounding
senpi install git:github.com/code-yeongyu/pi-openai-api-parallel-tool-calls # OpenAI parallel_tool_calls payload support
See Senpi Packages for the full install / update / remove flow.
Allow all permissions (OMO-style)
OMO runs with all tool permissions pre-approved. To replicate that behavior in senpi, add a wildcard allow rule to your global settings:
mkdir -p ~/.senpi/agent
cat > ~/.senpi/agent/settings.json << 'EOF'
{
"permission": {
"*": "allow"
}
}
EOF
This tells the permission system to auto-approve every tool call without prompting. The "*" key matches all permission names, and "allow" grants them unconditionally. You can also set this per-project by placing the same settings.json in .senpi/settings.json at the project root.
Note: This disables all interactive permission prompts. Only do this if you trust the model and the workspace you are running in.
No direct senpi counterpart
These are part of OMO's opencode harness shape and are intentionally not in senpi:
- Discipline Agents (Sisyphus / Hephaestus / Oracle / Librarian / Explore / Multimodal Looker) and the
ultrawork/ulwone-word orchestration entrypoint. - Team Mode — lead + up to 8 parallel members, tmux visualization,
team_*tool family,hyperplan/security-researchskills riding on top. - Hashline / hash-anchored edit tool — senpi stays with pi's standard
edit/multiedit/apply_patch.pi-comment-checkercovers the post-edit validation slot OMO uses Hashline for, just withoutLINE#IDcontent-hash identifiers. - Skill system and skill-embedded MCPs — skills as a first-class concept (
SKILL.md, scoped per-skill MCP servers) do not exist in senpi. - Prometheus interview-mode planner and the Ralph Loop /
/ulw-loopself-referential loop. /init-deep— there is no in-tree generator. Generate the hierarchicalAGENTS.mdtree manually (or with a normal agent prompt); the builtinnested-agents-mdextension will read the resulting files.- Built-in
doctorcommand, Claude Code hook/command/skill/plugin compatibility layer, and the agent category router (visual-engineering/deep/quick/ultrabrain).
Want more? Try the pi-extensions ecosystem
senpi ships a fixed set of builtin extensions and stops there. The code-yeongyu/pi-* GitHub repos contain the full extension ecosystem: some packages are vendored into senpi as builtins, while the rest can be installed on top when you want extra capabilities such as LSP or AST-grep.
Installable extensions
These code-yeongyu/pi-* packages are intended to be installed as standalone senpi/pi extensions:
| Extension | What it adds |
|---|---|
pi-anthropic-code-execution | Anthropic-native code execution. |
pi-anthropic-computer-use | Anthropic computer-use bindings. |
pi-anthropic-text-editor | Anthropic-native text editor tool. |
pi-anthropic-tool-search | Anthropic-native tool search. |
pi-anthropic-web-fetch | Anthropic-native web fetch support. |
pi-ast-grep | AST-aware code search/replace across 25 languages. Auto-downloads sg on first use. |
pi-comment-checker | Runs comment-quality checks after file-editing tools and shows warnings in the TUI. |
pi-cua-integration | Computer-use action wiring for desktop/browser interaction surfaces. |
pi-google-code-execution | Google native code execution. |
pi-google-google-search | Google Search grounding. |
pi-google-url-context | Google URL grounding. |
pi-lsp-client | LSP integration: lsp_rename, lsp_goto_definition, lsp_find_references, lsp_diagnostics, plus a /lsp inspector. |
pi-openai-api-parallel-tool-calls | OpenAI parallel_tool_calls payload support. |
pi-openai-code-interpreter | OpenAI Code Interpreter. |
Install any of them with:
senpi install git:github.com/code-yeongyu/pi-ast-grep
senpi install git:github.com/code-yeongyu/pi-lsp-client
# ...substitute any of the package names from the table above.
See Senpi Packages for the install / update / remove flow.
pi-extension packages already shipped as senpi builtins
You do not need to install these packages for normal senpi use; their functionality is already included in the binary. This table is intentionally limited to packages that map to the currently registered builtinExtensions list:
| Package | Included as | Builtin capability |
|---|---|---|
pi-anthropic-web-search | anthropic-web-search | Anthropic-native web search support. |
pi-apply-patch | gpt-apply-patch | Codex-style apply_patch tool for GPT-family runs. |
pi-bash-timeout | bash-timeout | Bash timeout defaults, max timeout enforcement, and prompt policy. |
pi-goal | goal | Persistent goal tracking, TUI status, and continuation prompts. |
pi-nested-agents-md | nested-agents-md | Auto-injects nearby AGENTS.md files for nested directories. |
pi-openai-web-search | openai-web-search | OpenAI Responses native web search. |
pi-rules | rules | Discovers project and user rule files, including AGENTS.md and CLAUDE.md. |
pi-todotools | todowrite | todowrite / todoread, todo sidebar state, workflow prompt guidance, and continuation follow-ups. |
pi-webfetch | webfetch | Fetches URL content as markdown, text, or HTML with bounded time and size. |
pi-websearch | websearch | Provider-backed web search with config-gated activation and source-aware results. |
Other builtins such as permission-system, prompt-preset, anthropic-bash, service-tier, tool-pair-guard, compaction, history-search, and session-observer are senpi-owned builtin extensions without installable sibling packages.
Why "senpi"
senpi is a small joke on senpai, but it is also literal project positioning: this fork aims to be a more sane pi with practical additions that make everyday agent work smoother without abandoning upstream's core design.
All additions follow pi's extension-first philosophy. Core source modifications are minimized and documented in changes.md files to keep upstream merge commits reviewable.
What this fork adds
senpi inherits pi's extension-first design — the core stays minimal, every feature lands as a builtin extension. The bet is that an opinionated set of features is wanted often enough to be in the binary; anything you don't want is still one settings flag away from being off (disabledBuiltinExtensions in settings.json).
Verified against git diff upstream/main..HEAD and every changes.md file in the repo.
New core subsystems
| Subsystem | What it does | Docs |
|---|---|---|
| Dynamic system prompt | Replaces upstream's static prompt with an adaptive builder: senpi identity → forced intent gate → exploration discipline → parallel-tool guidance → verification tiers → categorized tool reference → policies → style → optional per-model tuning. | dynamic-prompt/ · changes.md |
| Compaction pipeline | Plugsuit-style adaptive thresholds, empty-summarization guard, branch summarization hooks. Speculative + emergency compaction with restoration tracker lives as the compaction builtin extension. | core/compaction/ · changes.md |
| Tool-call middleware rewrite | XML / Hermes / YAML+XML / Gemma4 text-tool protocols for models without native function calling. Strict parsing, stream-error preservation. | tool-call-middleware/ · changes.md |
Owned builtin extensions
In-tree, tightly coupled to senpi internals. Loaded in this exact registration order:
| # | Extension | Role | Docs |
|---|---|---|---|
| 1 | permission-system | Full opencode-style permission port — rules, JSONL storage, TUI prompts, parser-aware patterns (bash arity, file globs, apply_patch body paths), non-interactive fallback | AGENTS.md · changes.md |
| 2 | gpt-apply-patch (vendored) | When the active model is OpenAI GPT, swaps write/edit for Codex-style freeform apply_patch with a Lark grammar. Synced from code-yeongyu/pi-apply-patch. | AGENTS.md |
| 3 | prompt-preset | Per-model system prompt presets (gpt-5.x, claude-opus-4-{5,6,7}, kimi-k2-6) layered on top of the dynamic prompt. Shared codex-style file-operations tuning. | AGENTS.md · changes.md |
| 4 | todowrite (vendored) | todowrite / todoread tools with branch-aware persistence, sidebar widget, workflow prompt guidance, and a continuation loop. Synced from code-yeongyu/pi-todotools. | — |
| 5 | redraws | /tui command reporting cumulative TUI full-redraw count. Used for differential-rendering debugging. | — |
| 6 | anthropic-web-search | Anthropic native web_search tool | — |
| 7 | anthropic-bash | Anthropic native bash tool variant | — |
| 8 | openai-web-search | OpenAI Responses native web_search | — |
| 9 | service-tier | Injects service_tier (auto / flex / priority) into OpenAI Responses payloads using per-model service tier or openai.serviceTier setting | — |
| 10 | bash-timeout (vendored) | Injects default + max bash timeouts, appends policy to system prompt. Synced from code-yeongyu/pi-bash-timeout. | — |
| 11 | tool-pair-guard | Sanitizes Anthropic request payloads by removing orphan tool_result blocks — compaction safety | — |
| 12 | compaction | Speculative + emergency compaction policy: degradation monitor, circuit breaker, per-turn cap, todo bridging, checkpoint state, restoration tracker, tool-result truncation | AGENTS.md · changes.md |
| 13 | history-search | /history command — searches prompt history across sessions in an overlay | — |
| 14 | websearch | Provider-backed web_search tool with config-gated activation, TUI status, and source-aware results | — |
| 15 | webfetch | webfetch tool for URL content as markdown, text, or HTML with bounded time and size | — |
| 16 | nested-agents-md | Auto-injects nearby AGENTS.md files when the agent reads from nested directories | — |
| 17 | rules | Auto-discovers project rule files and exposes /rules / /reload-rules commands | — |
| 18 | goal | Persistent goal tracking tools, footer state, and continuation prompts | — |
The builtin directories above are new vs upstream
pi-mono— none exist inbadlogic/pi-mono. Vendored versions are pinned inexternal-versions.jsonand synced from the siblingpi-extensionscheckout withsync-builtin-extensions.mjs.
Standalone extension repositories
These are maintained as public code-yeongyu/pi-* repositories and can be installed through settings.json packages or senpi install git:github.com/code-yeongyu/<repo>.
| Extension | Repository | What it does |
|---|---|---|
pi-comment-checker | code-yeongyu/pi-comment-checker | Runs @code-yeongyu/comment-checker after write, edit, multiedit, and apply_patch, including OMO-compatible apply_patch metadata and raw Codex patch fallback; shows warnings in an above-editor widget |
Global default extensions
Not loaded as builtins; written once into ~/.senpi/agent/extensions/ on first run so you can edit or remove them locally.
| Extension | Source | What it does |
|---|---|---|
diff | diff.ts | /diff command — picks modified / deleted / new files from git status, opens VS Code's diff view |
files | files.ts | /files command — lists files read / written / edited in the current session branch, opens selected in VS Code |
prompt-url-widget | prompt-url-widget.ts | Detects GitHub PR / issue URLs in prompts, fetches title via gh, auto-sets the session name |
tps | tps.ts | Tokens-per-second notification (input / output / cache r/w / total / elapsed) after each agent turn |
Modified upstream packages
| Package | What changed | Reference |
|---|---|---|
packages/ai | Senpi-branded Codex originator and User-Agent, shared tool-pair-repair utility, OpenAI Responses custom/freeform tool support for apply_patch, Claude Opus 4.7 + "max" thinking level, extraBody pass-through across every provider, tool-call middleware rewrite | ai/src/changes.md |
packages/agent | Parallel tool completion emission (concurrent finalization, source-order results), inline UUIDv7 replacing the uuid dep, ES2021-safe harness diagnostics | agent/src/changes.md |
packages/tui | Differential rendering tightening: insert-scroll fast path, viewport remap repaint fix, flicker-budget regression tests (no post-init full clears, balanced DECSET 2026) | tui/src/changes.md |
packages/coding-agent | senpi branding, model config controls (upstreamModelId, serviceTier, favorite models, disable/whitelist/blacklist), non-blocking startup tool discovery, disabled startup update checks, bash promptSnippet swap to rg, generated default extension fast-path, senpi-branded outbound identity | Multiple changes.md files |
Other branding / runtime changes
| Change | Details |
|---|---|
senpi CLI identity | The coding agent identifies itself as senpi, uses .senpi/agent for config storage, and publishes to npm as @code-yeongyu/senpi. The installed executable remains senpi. |
| Senpi-branded outbound identity | Every outbound request emits senpi instead of pi: User-Agent (update check + Cloudflare + GitHub releases), X-OpenRouter-Title, OpenAI Codex originator + User-Agent. |
| No startup update checks | Removed npm registry version checking and package update prompts at launch. |
| Builtin extension UI grouping | Builtins render under a builtin/ group in the startup header, visually distinct from user and project extensions. |
| Updated model registry | models.generated.ts refreshed with latest model additions and deprecations. |
| Self-update target | senpi update senpi queries code-yeongyu/senpi releases, not upstream. |
Fork Strategy
This fork rebases periodically on upstream/main. To minimize merge conflicts:
- Extension-first: All features use pi's extension system as builtin extensions.
- Document core changes: Every upstream file modification has a corresponding
changes.mdin the affected subdirectory, documenting what changed, why, and expected conflict zones. - Remotes:
origin= code-yeongyu/senpi,upstream= badlogic/pi-mono.
Modified upstream files (high-impact, see per-directory changes.md for the rest):
| File | Change |
|---|---|
agent-session.ts | Calls buildDynamicSystemPrompt() instead of buildSystemPrompt(); unified compaction pipeline; model-switch system-prompt change |
resource-loader.ts | Removed SYSTEM.md / APPEND_SYSTEM.md discovery; added builtin extension loading; generated-default extension fast-path |
interactive-mode.ts | Builtin extension display formatting; disabled update checks; non-blocking startup tools; favorite-model cycling |
model-registry.ts | Custom upstreamModelId and serviceTier; provider/model disable/whitelist/blacklist; thinkingLevelMapMode |
settings-manager.ts | disabledBuiltinExtensions; favoriteModels; openai.serviceTier; steering default "all" |
agent-loop.ts (packages/agent) | executeToolCallsParallel() |
tui.ts (packages/tui) | Differential rendering fast paths + flicker-budget enforcement |
package.json | Rebranded the coding agent package and runtime identity to senpi |
Share your OSS coding agent sessions
If you use pi or other coding agents for open source work, please share your sessions.
Public OSS session data helps improve coding agents with real-world tasks, tool use, failures, and fixes instead of toy benchmarks.
For the full explanation, see this post on X.
To publish sessions, use badlogic/pi-share-hf. Read its README.md for setup instructions. All you need is a Hugging Face account, the Hugging Face CLI, and pi-share-hf.
You can also watch this video, where I show how I publish my pi-mono sessions.
I regularly publish my own pi-mono work sessions here:
- badlogicgames/pi-mono on Hugging Face
All Packages
| Package | Description |
|---|---|
| @earendil-works/pi-ai | Unified multi-provider LLM API with text streaming, tool calling, OAuth helpers, and image generation |
| @earendil-works/pi-agent-core | Agent runtime with tool calling and state management |
| senpi | Interactive coding agent CLI, rebranded as senpi |
| @code-yeongyu/senpi-codemode | Source-only codemode extension package with settings, kernel, bridge, and prelude building blocks |
| @earendil-works/pi-tui | Terminal UI library with differential rendering |
For Slack/chat automation and workflows see earendil-works/pi-chat.
Permissions & Containerization
senpi does not include a built-in container boundary for restricting filesystem, process, network, or credential access. By default, it runs with the permissions of the user and process that launched it.
If you need stronger boundaries, containerize senpi. See packages/coding-agent/docs/containerization.md for three patterns:
- OpenShell: run the whole
senpiprocess in a policy-controlled container. - Gondolin extension: keep
senpiand provider auth on the host while routing built-in tools and!commands into a local Linux micro-VM. - Plain Docker: run the whole
senpiprocess in a local container for simple isolation.
Contributing
See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents).
Development
npm install --ignore-scripts # Install all dependencies without running lifecycle scripts
npm run build # Build all packages
npm run check # Lint, format, and type check
npm test # Run tests (skips LLM-dependent tests without API keys)
./pi-test.sh # Live-API integration suite (env-gated; requires API keys)
npm run publish # Publish npm workspaces, including @code-yeongyu/senpi
Supply-chain hardening
We treat npm dependency changes as reviewed code changes.
- Direct external dependencies are pinned to exact versions. Internal workspace packages remain version-ranged.
.npmrcsetssave-exact=trueandmin-release-age=2to avoid same-day dependency releases during npm resolution.package-lock.jsonis the dependency ground truth. Pre-commit blocks accidental lockfile commits unlessPI_ALLOW_LOCKFILE_CHANGE=1is set.npm run checkverifies pinned direct deps, native TypeScript import compatibility, and the generated coding-agent publish dependency manifest.packages/coding-agent/publish-deps.lock.jsonis generated from the root lockfile for publish staging but is never shipped; publishing annpm-shrinkwrap.jsonbeside bundled dependencies breaks npm installs.- Release smoke tests use
npm run release:localto build, pack, and create isolated npm and Bun installs outside the repo before tagging a release. - Local release installs, documented npm installs, and
senpi update senpiuse--ignore-scriptswhere supported. - CI installs with
npm ci --ignore-scripts, and a scheduled GitHub workflow runsnpm audit --omit=devplusnpm audit signatures --omit=dev. - Shrinkwrap generation has an explicit allowlist for dependency lifecycle scripts; new lifecycle-script deps fail checks until reviewed.
Contributing
See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents).
License
MIT
Ganbare Ganbare Senpi
Hora, senpi senpi, senpi te kudasai! Ganbare ganbare senpi, gan ganbare ganbare senpi ora!
A tiny, completely unserious love letter to the Ganbare Ganbare Senpai meme that the project's name secretly bows to. Every time the rebase is clean and the tests are green, somewhere a kouhai whispers:
- C'mon senpi, c'mon! Ship the PR.
- Notice me, senpi. ...the diagnostics noticed first.
- Try harder, senpi! (she did look. and the build did pass.)
- You can do it, senpi! One more agent, one more tool, one more clean rebase.
- Ganbare, ganbare, senpi! 頑張れ頑張れ先輩! Do your best, do your best, senpai!
Yes, the entire project name is a senpai pun. Type strictly, run the tests, write a changes.md, keep the merge surface tiny — and gan ganbare ganbare senpi ora!
Shoutout to plugsuits: senpi's compaction system takes inspiration from its design.
Related repositories
prompts.chat is the largest open-source prompt library for AI, formerly called Awesome ChatGPT Prompts. It hosts curated prompts in CSV and Markdown, available as a public website, Hugging Face dataset, or self-hosted instance. The project supports multiple LLM providers including ChatGPT, Claude, Gemini, Llama, and Mistral. Self-hosting uses a Next.js setup wizard that configures authentication via GitHub, Google, or Azure AD, with PostgreSQL as the recommended database. CLI access, an MCP server, and a Claude Code plugin extend its reach into developer workflows. The codebase is MIT-licensed while prompt data falls under CC0. Its 166k GitHub stars make it an AI resource on the platform with 166k GitHub stars, and it has been cited by Harvard, Columbia, and Forbes.
prompts.chat is an open-source library of prompts written for AI chat assistants, first released in December 2022 under the name Awesome ChatGPT Prompts. The GitHub project has since grown and now distributes prompts through a website, a CSV file, a Markdown file, and a Hugging Face dataset, alongside a self-hosting option, a CLI, an MCP server, and a Claude Code plugin.
Dify is an open-source LLM app platform that packages a visual workflow/agent builder, RAG pipeline, model provider management, and app-level APIs into one self-hostable (or cloud) stack, aimed at teams who want to skip stitching those pieces together themselves.
LangChain is a Python framework (MIT-licensed) for assembling LLM-powered apps and agents from standard components: model wrappers, prompts, retrieval, tools, and chain/graph orchestration handed off to LangGraph. It's for developers gluing together model providers and data sources, not for a single prompt-response call.
Quick answers
Does code-yeongyu/senpi have a project website?
No homepage URL was recorded for code-yeongyu/senpi in TopGit's last sync. The README tab above frequently contains screenshots and demo links, or check the repository description on GitHub.
How does code-yeongyu/senpi compare to other AI Tools projects?
code-yeongyu/senpi is tracked by TopGit in the AI Tools category, with 391 GitHub stars and written in TypeScript. Browse the AI Tools topic page on TopGit to compare it against similar projects by stars and activity.
How many stars does code-yeongyu/senpi have?
code-yeongyu/senpi has 391 GitHub stars — refresh the page for the live number, or check github.com/code-yeongyu/senpi. TopGit mirrors GitHub's count but does not claim minute-by-minute accuracy.
Is code-yeongyu/senpi open source?
Yes — code-yeongyu/senpi ships under the MIT license, which makes its source code freely readable (and, depending on license terms, forkable and reusable). Source: github.com/code-yeongyu/senpi.
What else is in the AI Tools space?
code-yeongyu/senpi is tracked by TopGit under the AI Tools category, alongside 12 GitHub-tagged topics. Trending and Topics pages list peer repositories of comparable stars and language.
What is code-yeongyu/senpi?
code-yeongyu/senpi (code-yeongyu/senpi) is a TypeScript project on GitHub. From the project's own README: pi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. opinionated fork of badlogic/pi-mono with extension-first additions. ganbare ganbare senpi 頑張れ頑張れ先輩
Where do I read more about code-yeongyu/senpi?
This TopGit page is a snapshot — the READ ME tab shows the project's own README content (links stripped, images preserved). The GitHub repository at github.com/code-yeongyu/senpi is the definitive source.
Read full README in the tab above.
Want a second opinion on senpi?
Ask an AI that can read this page — one click and you get its take on senpi.