pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-07-26 09:52:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

docs: enhance README formatting with tables for better structure and readability

Browse Source
This commit is contained in:
diegosouzapw
2026-07-24 12:31:19 -03:00
parent e8719783ef
commit 0f226a5a24
1 changed files with 150 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

275
README.md
View File

@@ -247,14 +247,15 @@ curl http://localhost:20128/v1/chat/completions \
No combo to create. Set your model to `auto` (or a variant) and OmniRoute builds a virtual combo from your connected providers, scored live:
| Model ID | What it optimizes for                                                                                                                                                                  |
| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `auto` | 🎯 Balanced default (LKGP — sticks to your last good provider) |
| `auto/coding` | 🧑‍💻 Quality-first weights for code generation |
| `auto/fast` | ⚡ Lowest latency first |
| `auto/cheap` | 💰 Cheapest per token first |
| `auto/offline` | 🔋 Most quota / rate-limit headroom first |
| `auto/smart` | 🔭 Quality-first + 10% exploration to discover better models |
<table>
<tr><th align="left">Model ID</th><th align="left">What it optimizes for</th></tr>
<tr><td align="left" nowrap><code>auto</code></td><td align="left">🎯 Balanced default (LKGP — sticks to your last good provider)</td></tr>
<tr><td align="left" nowrap><code>auto/coding</code></td><td align="left">🧑‍💻 Quality-first weights for code generation</td></tr>
<tr><td align="left" nowrap><code>auto/fast</code></td><td align="left">⚡ Lowest latency first</td></tr>
<tr><td align="left" nowrap><code>auto/cheap</code></td><td align="left">💰 Cheapest per token first</td></tr>
<tr><td align="left" nowrap><code>auto/offline</code></td><td align="left">🔋 Most quota / rate-limit headroom first</td></tr>
<tr><td align="left" nowrap><code>auto/smart</code></td><td align="left">🔭 Quality-first + 10% exploration to discover better models</td></tr>
</table>
##
@@ -556,16 +557,17 @@ OmniRoute is free and open source, built and maintained in the open. If it saves
> Same app, your machine, your rules. From a global npm install to **your phone** via Termux.
| Platform | Install | Highlights |
| ------------------------- | ---------------------------------------- | --------------------------------------------------------- |
| 📦 **npm (global)** | `npm install -g omniroute` | One command, any OS |
| 🐳 **Docker** | `docker run … diegosouzapw/omniroute` | Multi-arch **AMD64 + ARM64** |
| 🖥️ **Desktop (Electron)** | `npm run electron:build` | Native window + system tray — **Windows / macOS / Linux** |
| 💪 **ARM** | native `arm64` | Raspberry Pi, ARM servers, Apple Silicon |
| 📱 **Android (Termux)** | `pkg install nodejs && npx -y omniroute` | Runs **on your phone**, 24/7, no root |
| 📲 **PWA** | "Add to Home Screen" | Fullscreen, offline, installable from browser |
| 🧩 **OpenCode plugin** | `@omniroute/opencode-provider` | Native OpenCode integration |
| 🛠️ **From source** | `npm install && npm run dev` | Hack on it, contribute |
<table>
<tr><th align="left">Platform</th><th align="left">Install</th><th align="left">Highlights</th></tr>
<tr><td align="left" nowrap>📦 <b>npm (global)</b></td><td align="left" nowrap><code>npm install -g omniroute</code></td><td align="left">One command, any OS</td></tr>
<tr><td align="left" nowrap>🐳 <b>Docker</b></td><td align="left" nowrap><code>docker run … diegosouzapw/omniroute</code></td><td align="left">Multi-arch <b>AMD64 + ARM64</b></td></tr>
<tr><td align="left" nowrap>🖥️ <b>Desktop (Electron)</b></td><td align="left" nowrap><code>npm run electron:build</code></td><td align="left">Native window + system tray — <b>Windows / macOS / Linux</b></td></tr>
<tr><td align="left" nowrap>💪 <b>ARM</b></td><td align="left" nowrap>native <code>arm64</code></td><td align="left">Raspberry Pi, ARM servers, Apple Silicon</td></tr>
<tr><td align="left" nowrap>📱 <b>Android (Termux)</b></td><td align="left" nowrap><code>pkg install nodejs && npx -y omniroute</code></td><td align="left">Runs <b>on your phone</b>, 24/7, no root</td></tr>
<tr><td align="left" nowrap>📲 <b>PWA</b></td><td align="left" nowrap>"Add to Home Screen"</td><td align="left">Fullscreen, offline, installable from browser</td></tr>
<tr><td align="left" nowrap>🧩 <b>OpenCode plugin</b></td><td align="left" nowrap><code>@omniroute/opencode-provider</code></td><td align="left">Native OpenCode integration</td></tr>
<tr><td align="left" nowrap>🛠️ <b>From source</b></td><td align="left" nowrap><code>npm install && npm run dev</code></td><td align="left">Hack on it, contribute</td></tr>
</table>
<sub>📖 [Docker Guide](docs/guides/DOCKER_GUIDE.md) · [Desktop](electron/README.md) · [Termux](docs/guides/TERMUX_GUIDE.md) · [PWA](docs/guides/PWA_GUIDE.md) · [OpenCode](docs/frameworks/OPENCODE.md)</sub>
@@ -626,15 +628,16 @@ Tokens are scoped `read` / `write` / `admin`; process-spawning routes stay loopb
Expose OmniRoute over **MCP**, **A2A**, a **REST API**, **webhooks** or a **remote CLI** — any capable agent (or your own code) gets the keys to the whole gateway: routing, providers, combos, cache, compression, memory — autonomously. HTTP endpoints below are served under `http://localhost:20128`.
| Interface | Endpoint / command | Use it for |
| ------------------ | -------------------------- | -------------------------------------------------------- |
| 🧰 **MCP (stdio)** | `omniroute --mcp` | Plug into Claude Desktop, Cursor, any MCP client |
| 🌊 **MCP (HTTP)** | `/api/mcp/stream` | Remote MCP — **104 tools**, 31 scopes, full audit trail |
| 📡 **MCP (SSE)** | `/api/mcp/sse` | Streaming MCP transport |
| 🤝 **A2A** | `/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 6 skills |
| 🌐 **REST API** | `/v1/*` | OpenAI-compatible — chat, embeddings, images, audio, OCR |
| 🔔 **Webhooks** | `/api/webhooks` | Push events (usage, quota, errors, routing) to your URL |
| 🛰️ **Remote CLI** | `omniroute connect <host>` | Drive a remote instance with scoped access tokens |
<table>
<tr><th align="left">Interface</th><th align="left">Endpoint / command</th><th align="left">Use it for</th></tr>
<tr><td align="left" nowrap>🧰 <b>MCP (stdio)</b></td><td align="left" nowrap><code>omniroute --mcp</code></td><td align="left">Plug into Claude Desktop, Cursor, any MCP client</td></tr>
<tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>104 tools</b>, 31 scopes, full audit trail</td></tr>
<tr><td align="left" nowrap>📡 <b>MCP (SSE)</b></td><td align="left" nowrap><code>/api/mcp/sse</code></td><td align="left">Streaming MCP transport</td></tr>
<tr><td align="left" nowrap>🤝 <b>A2A</b></td><td align="left" nowrap><code>/.well-known/agent.json</code></td><td align="left">Agent-to-agent, <b>JSON-RPC 2.0</b> + SSE, 6 skills</td></tr>
<tr><td align="left" nowrap>🌐 <b>REST API</b></td><td align="left" nowrap><code>/v1/*</code></td><td align="left">OpenAI-compatible — chat, embeddings, images, audio, OCR</td></tr>
<tr><td align="left" nowrap>🔔 <b>Webhooks</b></td><td align="left" nowrap><code>/api/webhooks</code></td><td align="left">Push events (usage, quota, errors, routing) to your URL</td></tr>
<tr><td align="left" nowrap>🛰️ <b>Remote CLI</b></td><td align="left" nowrap><code>omniroute connect <host></code></td><td align="left">Drive a remote instance with scoped access tokens</td></tr>
</table>
```bash
# Give Claude Code the full OmniRoute toolset over MCP:
@@ -671,31 +674,33 @@ Code blocks, URLs, JSON and structured data are **always protected** by the pres
Engines run in pipeline order; each is independently toggleable and configurable per combo:
| # | Engine | What it does |
| --- | ------------------------- | --------------------------------------------------------------------------------------------------------- |
| 1 | **Session-Dedup** | Drops content repeated across turns (content-addressed, cross-turn) |
| 2 | **CCR** | Archives large blocks behind retrieve markers, fetched on demand |
| 3 | **Lite** | Whitespace + image-URL trimming (latency-light baseline) |
| 4 | **RTK** | Smart tool-result filtering, dedup & truncation (command-aware) |
| 5 | **Responses Tool Output** | Lossless-first JSON + bounded diagnostic compression for shell/patch/search/build outputs (Responses API) |
| 6 | **Headroom** | Lossless tabular compaction of JSON arrays (~30%) via a vendored **GCF** codec |
| 7 | **Relevance** | Extractive sentence scoring against the last user query |
| 8 | **Caveman** | Rule-based prose compression (~65–75% on output) |
| 9 | **Aggressive** | Summarization + progressive aging of old turns |
| 10 | **LLMLingua-2** | ML semantic pruning via MobileBERT ONNX — code-safe, async |
| 11 | **Ultra** | Heuristic token pruning with an optional small-model (SLM) tier |
| 12 | **OmniGlyph** | Experimental context-as-image encoding routed to Claude Fable 5 (most aggressive; opt-in) |
<table>
<tr><th align="center">#</th><th align="left">Engine</th><th align="left">What it does</th></tr>
<tr><td align="center" nowrap>1</td><td align="left" nowrap><b>Session-Dedup</b></td><td align="left">Drops content repeated across turns (content-addressed, cross-turn)</td></tr>
<tr><td align="center" nowrap>2</td><td align="left" nowrap><b>CCR</b></td><td align="left">Archives large blocks behind retrieve markers, fetched on demand</td></tr>
<tr><td align="center" nowrap>3</td><td align="left" nowrap><b>Lite</b></td><td align="left">Whitespace + image-URL trimming (latency-light baseline)</td></tr>
<tr><td align="center" nowrap>4</td><td align="left" nowrap><b>RTK</b></td><td align="left">Smart tool-result filtering, dedup & truncation (command-aware)</td></tr>
<tr><td align="center" nowrap>5</td><td align="left" nowrap><b>Responses Tool Output</b></td><td align="left">Lossless-first JSON + bounded diagnostic compression for shell/patch/search/build outputs (Responses API)</td></tr>
<tr><td align="center" nowrap>6</td><td align="left" nowrap><b>Headroom</b></td><td align="left">Lossless tabular compaction of JSON arrays (~30%) via a vendored <b>GCF</b> codec</td></tr>
<tr><td align="center" nowrap>7</td><td align="left" nowrap><b>Relevance</b></td><td align="left">Extractive sentence scoring against the last user query</td></tr>
<tr><td align="center" nowrap>8</td><td align="left" nowrap><b>Caveman</b></td><td align="left">Rule-based prose compression (~65–75% on output)</td></tr>
<tr><td align="center" nowrap>9</td><td align="left" nowrap><b>Aggressive</b></td><td align="left">Summarization + progressive aging of old turns</td></tr>
<tr><td align="center" nowrap>10</td><td align="left" nowrap><b>LLMLingua-2</b></td><td align="left">ML semantic pruning via MobileBERT ONNX — code-safe, async</td></tr>
<tr><td align="center" nowrap>11</td><td align="left" nowrap><b>Ultra</b></td><td align="left">Heuristic token pruning with an optional small-model (SLM) tier</td></tr>
<tr><td align="center" nowrap>12</td><td align="left" nowrap><b>OmniGlyph</b></td><td align="left">Experimental context-as-image encoding routed to Claude Fable 5 (most aggressive; opt-in)</td></tr>
</table>
Code blocks, URLs and structured data are **always preserved** byte-perfect. **One-click presets** combine the engines:
| Mode | Savings | Best for                                                                                                                                        |
| ------------------------------ | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| 🪶 **Lite** | ~15% | Always-on safe default |
| 🪨 **Standard (Caveman)** | ~30% | Daily coding |
| ⚡ **Aggressive** | ~50% | Long tool-heavy sessions |
| 🔥 **Ultra** | ~75% | Maximum savings |
| 🧰 **RTK** | 60–90% | Shell/test/build/git output |
| 🔗 **Stacked (RTK → Caveman)** | **78–95%** | Mixed prompts + tool logs |
<table>
<tr><th align="left">Mode</th><th align="left">Savings</th><th align="left">Best for</th></tr>
<tr><td align="left" nowrap>🪶 <b>Lite</b></td><td align="left" nowrap>~15%</td><td align="left">Always-on safe default</td></tr>
<tr><td align="left" nowrap>🪨 <b>Standard (Caveman)</b></td><td align="left" nowrap>~30%</td><td align="left">Daily coding</td></tr>
<tr><td align="left" nowrap>⚡ <b>Aggressive</b></td><td align="left" nowrap>~50%</td><td align="left">Long tool-heavy sessions</td></tr>
<tr><td align="left" nowrap>🔥 <b>Ultra</b></td><td align="left" nowrap>~75%</td><td align="left">Maximum savings</td></tr>
<tr><td align="left" nowrap>🧰 <b>RTK</b></td><td align="left" nowrap>60–90%</td><td align="left">Shell/test/build/git output</td></tr>
<tr><td align="left" nowrap>🔗 <b>Stacked (RTK → Caveman)</b></td><td align="left" nowrap><b>78–95%</b></td><td align="left">Mixed prompts + tool logs</td></tr>
</table>
**Real example — Standard mode:**
@@ -924,21 +929,26 @@ same process on one port, so there is no separate CLI-only package today.
</div>
- **Runtime**: Node.js 22.x or 24.x LTS (24 LTS recommended) — `>=22.22.2 <23 || >=24.0.0 <27`
- **Language**: TypeScript 6.0 — **100% TypeScript** across `src/` and `open-sse/` (zero `any` in core modules since v2.0)
- **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
- **Database**: better-sqlite3 (SQLite) + LowDB (JSON legacy) — domain state, proxy logs, MCP audit, routing decisions, memory, skills
- **Schemas**: Zod (MCP tool I/O validation, API contracts)
- **Protocols**: MCP (stdio/HTTP) + A2A v0.3 (JSON-RPC 2.0 + SSE)
- **Streaming**: Server-Sent Events (SSE) + WebSocket bridge (`/v1/ws`)
- **Auth**: OAuth 2.0 (PKCE) + JWT + API Keys + MCP Scoped Authorization
- **Testing**: Node.js test runner + Vitest (**25,000+ test cases** across 3,300+ files — unit, integration, E2E, security, ecosystem)
- **Platforms**: Desktop (Electron), Android (Termux), PWA (any browser)
- **CI/CD**: GitHub Actions (auto npm publish + Docker Hub on release)
- **Website**: [omniroute.online](https://omniroute.online)
- **Package**: [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
- **Docker**: [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
- **Resilience**: Circuit breaker, exponential backoff, anti-thundering herd, TLS spoofing, auto-combo self-healing
<table>
<tr><th align="left">Layer</th><th align="left">Technology</th></tr>
<tr><td nowrap><b>Runtime</b></td><td>Node.js 22.x / 24.x LTS — <code>&gt;=22.22.2 &lt;23 || &gt;=24.0.0 &lt;27</code></td></tr>
<tr><td nowrap><b>Language</b></td><td>TypeScript 6.0 — <b>100% TypeScript</b> across <code>src/</code> and <code>open-sse/</code> (zero <code>any</code> in core since v2.0)</td></tr>
<tr><td nowrap><b>Framework</b></td><td>Next.js 16 + React 19 + Tailwind CSS 4</td></tr>
<tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 95 domain modules, 110 migrations</td></tr>
<tr><td nowrap><b>Memory</b></td><td>SQLite FTS5 full-text + int8-quantized vector embeddings, typed decay</td></tr>
<tr><td nowrap><b>Schemas</b></td><td>Zod 4 — MCP tool I/O validation + API contracts</td></tr>
<tr><td nowrap><b>Protocols</b></td><td>MCP (stdio / HTTP / SSE) + A2A v0.3 (JSON-RPC 2.0 + SSE)</td></tr>
<tr><td nowrap><b>Streaming</b></td><td>Server-Sent Events (SSE) + WebSocket bridge (<code>/v1/ws</code>)</td></tr>
<tr><td nowrap><b>Compression</b></td><td>12-engine pipeline — RTK, Caveman, LLMLingua-2 (MobileBERT ONNX), GCF, OmniGlyph</td></tr>
<tr><td nowrap><b>Auth &amp; security</b></td><td>OAuth 2.0 (PKCE) + JWT + API Keys + MCP scoped auth · AES-256-GCM at rest · DOMPurify</td></tr>
<tr><td nowrap><b>Stealth</b></td><td>wreq-js — JA3 / JA4 TLS fingerprint impersonation, 3-level proxy</td></tr>
<tr><td nowrap><b>Resilience</b></td><td>Circuit breaker, exponential backoff, anti-thundering-herd, auto-combo self-healing</td></tr>
<tr><td nowrap><b>Logging</b></td><td>pino — structured JSON logs with request context</td></tr>
<tr><td nowrap><b>Testing</b></td><td>Node.js test runner + Vitest — <b>25,000+ test cases</b> across 3,300+ files (unit, integration, E2E, security, ecosystem)</td></tr>
<tr><td nowrap><b>Platforms</b></td><td>Desktop (Electron) · Android (Termux) · PWA (any browser)</td></tr>
<tr><td nowrap><b>CI/CD</b></td><td>GitHub Actions — auto npm publish + Docker Hub on release</td></tr>
<tr><td nowrap><b>Links</b></td><td><a href="https://omniroute.online">Website</a> · <a href="https://www.npmjs.com/package/omniroute">npm</a> · <a href="https://hub.docker.com/r/diegosouzapw/omniroute">Docker Hub</a></td></tr>
</table>
<div align="center">
@@ -1107,19 +1117,34 @@ same process on one port, so there is no separate CLI-only package today.
## 💖 Sponsors
A heartfelt thank-you to the people who fund OmniRoute out of their own pocket. Every contribution keeps the project free, independent and moving.
<div align="center">
<p align="center">
<a href="https://github.com/igormorais123"><img src="https://github.com/igormorais123.png?size=140" width="80" alt="Professor Igor Morais Vasconcelos (@igormorais123)"/></a>
&nbsp;&nbsp;&nbsp;
<a href="https://github.com/longtao77"><img src="https://github.com/longtao77.png?size=140" width="80" alt="longtao (@longtao77)"/></a>
</p>
A heartfelt thank-you to the people who fund OmniRoute out of their own pocket — every contribution keeps the project free, independent and moving.
<p align="center">
<sub><b><a href="https://github.com/igormorais123">Professor Igor Morais Vasconcelos</a></b> &nbsp;·&nbsp; <b><a href="https://github.com/longtao77">longtao</a></b> &nbsp;·&nbsp; and others who prefer to stay private 💛</sub>
</p>
<table>
<tr>
<td align="center" width="180">
<a href="https://github.com/igormorais123">
<img src="https://github.com/igormorais123.png?size=140" width="72" style="border-radius:50%" alt="Professor Igor Morais Vasconcelos"/><br/>
<b>Prof. Igor Morais</b>
</a><br/>
<sub>💛 Sponsor</sub>
</td>
<td align="center" width="180">
<a href="https://github.com/longtao77">
<img src="https://github.com/longtao77.png?size=140" width="72" style="border-radius:50%" alt="longtao"/><br/>
<b>longtao</b>
</a><br/>
<sub>💛 Sponsor</sub>
</td>
</tr>
</table>
> **Want to support OmniRoute?** <a href="https://github.com/sponsors/diegosouzapw"><b>Become a sponsor →</b></a> Every dollar goes straight into keeping the project free and independent.
<sub>… and others who prefer to stay private 💛</sub>
<b><a href="https://github.com/sponsors/diegosouzapw">💖 Become a sponsor →</a></b> — every dollar keeps OmniRoute free and independent.
</div>
<br/>
@@ -1192,78 +1217,78 @@ OmniRoute stands on the shoulders of giants. It started as a fork of **[9router]
### 🧬 Lineage & gateway
| Project | ⭐ | How it inspired OmniRoute |
| ------------------------------------------------------------------------------- | ----: | ------------------------------------------------------------------------------------------------------------------------------------- |
| **[9router](https://github.com/decolua/9router)** · decolua | 22.7k | The original project this fork is built on — extended here with multi-modal APIs and a full TypeScript rewrite. |
| **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** · router-for-me | 43.6k | The Go implementation that inspired this JavaScript / TypeScript port. |
| **[LiteLLM](https://github.com/BerriAI/litellm)** · BerriAI | 54.0k | The AI gateway whose public pricing dataset feeds our cost-tracking sync and whose provider-normalization model informed our routing. |
| Project | ⭐ |
| :-------------------------------------------------------------- | :---: |
| **[9router](https://github.com/decolua/9router)** | 22.7k |
| **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** | 43.6k |
| **[LiteLLM](https://github.com/BerriAI/litellm)** | 54.0k |
### 🗜️ Context & token compression — engines
| Project | ⭐ | How it inspired OmniRoute |
| ----------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **[Caveman](https://github.com/JuliusBrussee/caveman)** · JuliusBrussee | 90.8k | The viral "why use many token when few token do trick" project — its caveman-speak philosophy powers our standard compression mode and 30+ filler/condensation rules. |
| **[RTK – Rust Token Killer](https://github.com/rtk-ai/rtk)** · rtk-ai | 71.8k | High-performance command-output compression — inspired our RTK engine, JSON filter DSL, raw-output recovery and the stacked RTK → Caveman pipeline. |
| **[headroom](https://github.com/headroomlabs-ai/headroom)** · headroomlabs-ai | 60.1k | Reversible context-compression (SmartCrusher) — inspired our `headroom` engine and the `ccr` retrieve-marker pattern. |
| **[LLMLingua](https://github.com/microsoft/LLMLingua)** · Microsoft | 6.5k | Prompt-compression research (LLMLingua / LLMLingua-2) — inspired our async, code-safe, fail-open `llmlingua` engine. |
| **[llmlingua-2-js](https://github.com/atjsh/llmlingua-2-js)** · atjsh | 30 | The JS/ONNX port (MobileBERT / XLM-RoBERTa) used as the worker-thread backend for our LLMLingua engine. |
| **[Troglodita](https://github.com/leninejunior/troglodita)** · Lenine Júnior | 26 | PT-BR token compression — powers our pt-BR language pack: pleonasm reduction and filler removal tuned for Brazilian-Portuguese grammar. |
| **[ponytail](https://github.com/DietrichGebert/ponytail)** · DietrichGebert | 86.0k | The viral "lazy senior dev" YAGNI-coder skill — inspired our **less-code** Output Style: smallest-working-change steering that cuts _generated_ code (the output-axis sibling to Caveman's terse prose). |
| Project | ⭐ |
| :------------------------------------------------------------ | :---: |
| **[Caveman](https://github.com/JuliusBrussee/caveman)** | 90.8k |
| **[RTK – Rust Token Killer](https://github.com/rtk-ai/rtk)** | 71.8k |
| **[headroom](https://github.com/headroomlabs-ai/headroom)** | 60.1k |
| **[LLMLingua](https://github.com/microsoft/LLMLingua)** | 6.5k |
| **[llmlingua-2-js](https://github.com/atjsh/llmlingua-2-js)** | 30 |
| **[Troglodita](https://github.com/leninejunior/troglodita)** | 26 |
| **[ponytail](https://github.com/DietrichGebert/ponytail)** | 86.0k |
### 🧩 Compact formats, token research & code-aware tooling
| Project | ⭐ | How it inspired OmniRoute |
| ---------------------------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **[TOON](https://github.com/toon-format/toon)** · toon-format | 24.9k | Token-Oriented Object Notation — its columnar, header-plus-rows model shaped our tabular compaction stage. |
| **[GCF – Graph Compact Format](https://github.com/blackwell-systems/gcf)** · Blackwell Systems | 22 | First inspired our tabular compaction stage; now its zero-dependency, lossless generic-profile encoder is **vendored directly** as the Headroom codec (MIT, SPDX-marked), current with GCF spec v3.2. |
| **[token-optimizer-mcp](https://github.com/ooples/token-optimizer-mcp)** · ooples | 444 | Brotli/SQLite cache + per-session context-delta — inspired our `session-dedup` engine. |
| **[token-savior](https://github.com/Mibayy/token-savior)** · Mibayy | 1.1k | Bash-output compaction + MCP profiles — inspired our compression bail-out discipline and MCP tool-manifest reduction. |
| **[token-saver](https://github.com/ppgranger/token-saver)** · ppgranger | 117 | Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip. |
| **[token-optimizer](https://github.com/alexgreensh/token-optimizer)** · alexgreensh | 1.7k | "Find the ghost tokens" — its offload + recoverable-handle pattern informed our CCR offload thinking. |
| **[TokenMizer](https://github.com/Shweta-Mishra-ai/tokenmizer)** · Shweta-Mishra-ai | 16 | A session-graph + cross-turn line-dedup blueprint that informed our session-dedup design. |
| **[OmniCompress](https://github.com/jessefreitas/OmniCompress)** · jessefreitas | 3 | Rust columnar-JSON + content-addressed retrieve + cross-message dedup — validated our `headroom`/`ccr`/`session-dedup` engine design and the cache-stable "compressed form is position-independent" invariant. |
| **[mcp-compressor](https://github.com/atlassian-labs/mcp-compressor)** · Atlassian Labs | 98 | MCP tool-schema/description compression — informed our MCP tool-manifest cardinality reduction. |
| **[RepoMapper](https://github.com/pdavis68/RepoMapper)** · pdavis68 | 187 | Aider-style repo-map ranking — informed our repo-map / retrieval-ranking exploration. |
| **[quiet-shell-mcp](https://github.com/mrsimpson/quiet-shell-mcp)** · mrsimpson | 4 | Declarative shell-output reduction over MCP — validated our declarative bash-output compaction. |
| **[ts-morph](https://github.com/dsherret/ts-morph)** · David Sherret | 6.1k | TypeScript Compiler API toolkit — inspired our parser-based comment removal that preserves string, template and regex literals. |
| Project | ⭐ |
| :------------------------------------------------------------------------- | :---: |
| **[TOON](https://github.com/toon-format/toon)** | 24.9k |
| **[GCF – Graph Compact Format](https://github.com/blackwell-systems/gcf)** | 22 |
| **[token-optimizer-mcp](https://github.com/ooples/token-optimizer-mcp)** | 444 |
| **[token-savior](https://github.com/Mibayy/token-savior)** | 1.1k |
| **[token-saver](https://github.com/ppgranger/token-saver)** | 117 |
| **[token-optimizer](https://github.com/alexgreensh/token-optimizer)** | 1.7k |
| **[TokenMizer](https://github.com/Shweta-Mishra-ai/tokenmizer)** | 16 |
| **[OmniCompress](https://github.com/jessefreitas/OmniCompress)** | 3 |
| **[mcp-compressor](https://github.com/atlassian-labs/mcp-compressor)** | 98 |
| **[RepoMapper](https://github.com/pdavis68/RepoMapper)** | 187 |
| **[quiet-shell-mcp](https://github.com/mrsimpson/quiet-shell-mcp)** | 4 |
| **[ts-morph](https://github.com/dsherret/ts-morph)** | 6.1k |
### 🧠 Memory & RAG
| Project | ⭐ | How it inspired OmniRoute |
| ------------------------------------------------------------------ | ----: | ------------------------------------------------------------------------------------------------------------------- |
| **[Mem0](https://github.com/mem0ai/mem0)** · mem0ai | 61.2k | Universal memory layer — its proxy-as-write/read-boundary model shaped our memory architecture. |
| **[Letta (MemGPT)](https://github.com/letta-ai/letta)** · letta-ai | 23.9k | Stateful agents with tiered memory — inspired our Context Control & Recovery (CCR) tiered model. |
| **[WFGY](https://github.com/onestardao/WFGY)** · onestardao | 1.8k | The ProblemMap taxonomy of 16 recurring RAG/LLM failure modes — the shared vocabulary in our troubleshooting guide. |
| Project | ⭐ |
| :------------------------------------------------------ | :---: |
| **[Mem0](https://github.com/mem0ai/mem0)** | 61.2k |
| **[Letta (MemGPT)](https://github.com/letta-ai/letta)** | 23.9k |
| **[WFGY](https://github.com/onestardao/WFGY)** | 1.8k |
### 🛰️ Traffic inspection, MITM & transparent proxy
| Project | ⭐ | How it inspired OmniRoute |
| --------------------------------------------------------------------------------- | ---: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **[llm-interceptor](https://github.com/chouzz/llm-interceptor)** · chouzz | 49 | MITM interception/analysis of coding-assistant ↔ LLM traffic — our Traffic Inspector ports its SSE merge, conversation normalization, host passthrough and secret masking (MIT). |
| **[ProxyBridge](https://github.com/InterceptSuite/ProxyBridge)** · InterceptSuite | 5.5k | Transparent per-process proxy routing — inspired our crash-safe MITM teardown, socket idle-timeouts, `/proc` process attribution and TPROXY capture. |
| Project | ⭐ |
| :--------------------------------------------------------------- | :--: |
| **[llm-interceptor](https://github.com/chouzz/llm-interceptor)** | 49 |
| **[ProxyBridge](https://github.com/InterceptSuite/ProxyBridge)** | 5.5k |
### 📚 Model data, observability & UI
| Project | ⭐ | How it inspired OmniRoute |
| -------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------- |
| **[models.dev](https://github.com/anomalyco/models.dev)** · SST / OpenCode | 6.0k | Open database of AI model specs, pricing and capabilities — synced natively into our model catalog. |
| **[React Flow / xyflow](https://github.com/xyflow/xyflow)** · xyflow | 37.7k | The node-based graph library powering our real-time Compression Studio and Combo/Routing Studio. |
| **[LangGraph](https://github.com/langchain-ai/langgraph)** · LangChain | 37.6k | LangGraph Studio's live workflow-graph visualization inspired our Studios' real-time cascade view. |
| **[Langfuse](https://github.com/langfuse/langfuse)** · Langfuse | 31.4k | Its trace → span → generation observability model shaped our Compression Studio waterfall. |
| **[Kiali](https://github.com/kiali/kiali)** · Kiali | 3.6k | Istio service-mesh observability — inspired our circuit-breaker badges and error-edge visuals in the Routing/Combo Studio. |
| **[lobe-icons](https://github.com/lobehub/lobe-icons)** · LobeHub | 2.2k | AI/LLM brand logos that render the provider icons across our dashboard. |
| Project | ⭐ |
| :---------------------------------------------------------- | :---: |
| **[models.dev](https://github.com/anomalyco/models.dev)** | 6.0k |
| **[React Flow / xyflow](https://github.com/xyflow/xyflow)** | 37.7k |
| **[LangGraph](https://github.com/langchain-ai/langgraph)** | 37.6k |
| **[Langfuse](https://github.com/langfuse/langfuse)** | 31.4k |
| **[Kiali](https://github.com/kiali/kiali)** | 3.6k |
| **[lobe-icons](https://github.com/lobehub/lobe-icons)** | 2.2k |
### 🛡️ Security
| Project | ⭐ | How it inspired OmniRoute |
| ------------------------------------------------------------------------------------------- | --: | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| **[awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults)** · tldrsec | 710 | A curated list of secure-by-default libraries that guides our security choices (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink). |
| Project | ⭐ |
| :-------------------------------------------------------------------------------- | :-: |
| **[awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults)** | 710 |
### 🧭 Complementary tools
| Project | How it composes with OmniRoute |
| ----------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **[CodeWebChat](https://github.com/robertpiosik/CodeWebChat)** · robertpiosik | Editor-side companion — VS Code + browser extension that autofills 15+ chatbot web UIs with editor context. Owns the free-web-UI rail alongside OmniRoute's API rail; can point its API mode at OmniRoute. |
| Project | ⭐ |
| :------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| **[CodeWebChat](https://github.com/robertpiosik/CodeWebChat)** | Editor-side companion — VS Code + browser extension that autofills 15+ chatbot web UIs with editor context. Owns the free-web-UI rail alongside OmniRoute's API rail; can point its API mode at OmniRoute. |
## 📄 License