OmniRoute
CLAUDE.md83k starsChanged 10 days agoMITView on GitHub
All project rules live in AGENTS.md — the single source of truth for every AI assistant (architecture, conventions, testing, quality gates, git workflow, the 23 Hard Rules, PII learnings). Read it in full; do not re-add project rules here. Everything below applies ONLY to Claude Code — operational refinements of rules already defined in AGENTS.md. The full mandatory worktree protocol (base-branch confirmation, .claude/worktrees/ canonical path, cp -al nodemodules, teardown rules) is in docs/ops/WORKTREEISOLATION.md (summarized in AGENTS.md → Git Workflow →…
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Prefer the native EnterWorktree tool — it already creates worktrees under .claude/worktrees/ (the canonical path).
- Very specific: line 31
Before merging or pushing to any PR you did not create _this session_, run git worktree list and re-check gh pr view <N> --json …
- Very specific: line 49
Commit those artifacts inside the _tasks/ repo (git -C _tasks …), never in the main repo.
- Very specific: line 62
Do not confuse this with _tasks/ (Hard Rule #23, its own private git repo for durable plans/specs/research/hand-offs) — _artifacts/ is for …
- Very specific: line 68
Before cutting a branch or opening a PR, run the base-green check (AGENTS.md → Git Workflow → "Base-green check".
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
@AGENTS.md
All project rules live in AGENTS.md — the single source of truth for every AI
assistant (architecture, conventions, testing, quality gates, git workflow, the 23 Hard Rules,
PII learnings). Read it in full; do not re-add project rules here. Everything below applies ONLY
to Claude Code — operational refinements of rules already defined in AGENTS.md.
Worktree isolation — Claude Code specifics
The full mandatory worktree protocol (base-branch confirmation, .claude/worktrees/ canonical
path, cp -al node_modules, teardown rules) is in
docs/ops/WORKTREE_ISOLATION.md (summarized in AGENTS.md →
Git Workflow → "Worktree isolation"). Claude-Code-specific points:
- Confirm the base branch with the operator via
AskUserQuestion(Hard Rule #19) unless they already told you. - Prefer the native
EnterWorktreetool — it already creates worktrees under.claude/worktrees/(the canonical path). Create the worktree with the documentedgit worktree addcommand, then callEnterWorktreewith itspath.
Cross-session safety — Claude Code specifics
Hard Rules #19/#21/#22 (in AGENTS.md) govern parallel sessions. Operational reminders for this
harness:
- Replicate the
git stashban verbatim in the prompt of every subagent that touches git (Agent tool / Workflow scripts) — subagents do not inherit this file, and the recorded recurrence of the stash incident came through a subagent. - Before merging or pushing to any PR you did not create this session, run
git worktree listand re-checkgh pr view <N> --json state,headRefOid(Hard Rule #22b). - End every session with the main checkout on the branch it started on.
Superpowers / planning artifacts — path overrides
The _tasks/ convention is defined in AGENTS.md → "Planning & Research Artifacts". The
superpowers skills ship with defaults that point at docs/… — those defaults are overridden
here. When a superpowers skill announces a path like "saved to docs/superpowers/plans/…",
rewrite it to the _tasks/… equivalent before writing:
| Artifact (skill) | Default (do NOT use) | Save here instead |
Plans (writing-plans) | docs/superpowers/plans/ | _tasks/superpowers/plans/YYYY-MM-DD-<feature>.md |
Specs / design (brainstorming) | docs/superpowers/specs/ | _tasks/superpowers/specs/YYYY-MM-DD-<topic>-design.md |
Research (deep-research, ad-hoc) | docs/research/ | _tasks/research/… |
Hand-offs (/handoff) | — | _tasks/hands-off/<YYYY-MM-DD>_<branch>_v<versão>_sess-<id>/ |
Commit those artifacts inside the _tasks/ repo (git -C _tasks …), never in the main repo.
Scratch / temporary files — use _artifacts/, not /tmp
This project overrides the harness's default session scratchpad (/tmp/claude-*/…). Write
temporary/working files — exports, generated zips, one-off intermediate outputs, anything you'd
otherwise put in /tmp — to /home/diegosouzapw/dev/proxys/OmniRoute/_artifacts/ instead.
_artifacts/is a root_*path: already gitignored (AGENTS.md→ "Root_*paths"), lives on disk only, never tracked.- Reason: keeping scratch output inside the project (vs
/tmp) makes it trivial for the operator to find and delete everything temporary in one place, instead of hunting across ephemeral session-specific/tmpdirectories that vanish or accumulate untracked. - Do not confuse this with
_tasks/(Hard Rule #23, its own private git repo for durable plans/specs/research/hand-offs) —_artifacts/is for disposable working files only, nothing here needs to survive or be versioned.
Base-green before opening PRs
Before cutting a branch or opening a PR, run the base-green check (AGENTS.md → Git Workflow →
"Base-green check"; project skills reference it as .agents/skills/_shared/base-green.md). A PR
opened while the base tip is red must carry ⚠️ base-red inherited: #<issue> in its body. To
drain an accumulated red state (base tip + red PRs), use the /sweep-reds skill.
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Who's talking about cheaper-inference/OmniRoute
- Ravi Gupta“9 Billion AI Token free 🤯 These 2 GitHub repositories could help you explore free AI 👇🏻”YouTube · Oct 25, 2026 · 1.4k views
- AI씬 | AI뉴스 오픈소스“클로드 코드 '공짜'의 대가 | 별 23만 개 저장소들, 열어 보니”YouTube · Oct 27, 2026 · 975 views
- Compile Time“How to Use Claude Code for FREE in 2026 (Step-by-Step Guide) - Unlimited with OmniRoute - Part 1”YouTube · Oct 25, 2026 · 884 views
- Zaid Alsaleh“1.6 مليار توكن مجاناً كل شهر لكلود كود 🤯 أداة OmniRoute”YouTube · Oct 26, 2026 · 853 views
- Naveen | AI“OmniRoute: Use Claude Code, Cursor and Codex for Free #AIcoding #ClaudeCode #OpenSource”YouTube · Oct 23, 2026 · 507 views
The biggest 5 of 35 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 35
Talked about on YouTube, GitHub and the web (35 times).
On YouTube · 13
- Oct 25, 20269 Billion AI Token free 🤯 These 2 GitHub repositories could help you explore free AI 👇🏻 — Ravi Gupta1.4k views · 11 comments
- Oct 27, 2026클로드 코드 '공짜'의 대가 | 별 23만 개 저장소들, 열어 보니 — AI씬 | AI뉴스 오픈소스975 views
- Oct 25, 2026How to Use Claude Code for FREE in 2026 (Step-by-Step Guide) - Unlimited with OmniRoute - Part 1 — Compile Time884 views · 2 comments
- Oct 26, 20261.6 مليار توكن مجاناً كل شهر لكلود كود 🤯 أداة OmniRoute — Zaid Alsaleh853 views · 1 comment
- Oct 23, 2026OmniRoute: Use Claude Code, Cursor and Codex for Free #AIcoding #ClaudeCode #OpenSource — Naveen | AI507 views · 1 comment
8 more on YouTube
- Oct 26, 2026Never run out of Claude Code tokens (2 free repos) #shorts — Satwik JS288 views · 1 comment
- Oct 25, 2026Claude Code: 4 plugin đỡ tốn token nên cài ngay — VietlinhAI190 views
- Oct 26, 2026🔥 Claude Code for FREE? 2 GitHub Repos That Change Everything! 🤯 — WHAT IF ? LAB148 views · 2 comments
- Oct 26, 20262 Free AI Routers Share 1 Catch — WorkSmartOS97 views · 1 comment
- Oct 26, 2026Agent hit its quota? 150 free providers are next in line — thenightlybuild87 views
- Oct 23, 2026Best GitHub Repos For AI Agents 2024 #Shorts — AI Húp5 views
- Oct 27, 2026Claude Code ke 3 plugins jo tokens bachate hain (Ponytail, Graphify, OmniRoute) — Neural Drop Hindi0 views
- Oct 27, 20263 Claude Code plugins that save you tokens (Ponytail, Graphify, OmniRoute) — Neural Drop0 views
On GitHub · 11
- Oct 21, 2026feat(api): serve Jev combos through OpenCode Free and CommandCode — PixmaNts/OmniRoute1 reaction
- Oct 28, 2026Auto-discovery: 15 verified AI agent repos (2026-10-28) — tayyabimam1/awesome-ai-agent-stack0 reactions · 2 comments
- Oct 28, 2026Research and adapt architecture patterns from similar gateway/router projects — gordonpn/shunt-shim0 reactions
- Oct 27, 2026Implement tele-proxy: combo policies, durable accounting, and external observability — Kitkitkittt/tele-proxy0 reactions · 1 comment
- Oct 27, 2026[Candidate] cheaper-inference/omniroute - large collection (52 SKILL.md files) — ProSkillsMD/proskills0 reactions · 1 comment
6 more on GitHub
- Oct 26, 2026feat(decisions): prepare System One codec for Jev integration — ekinnee/omniroute-openclaw0 reactions
- Oct 26, 2026Catalogue digest — 2026-10-26 — vatsalp2008/AI-Agent-Discovery0 reactions
- Oct 25, 2026⚠️ Failed to create server discovery PR — fuzzylabs/awesome-secure-mcp-servers0 reactions
- Oct 22, 2026feat(providers): add the local MiniMax Code provider with native tool calling — megamen32/OmniRoute0 reactions
- Oct 22, 2026feat(omniroute): new add-on for OmniRoute AI inference gateway — alexbelgium/hassio-addons0 reactions · 6 comments
- Oct 21, 2026✏️ ახალი მისამართი: diegosouzapw/OmniRoute → cheaper-inference/OmniRoute — tornikebolokadze1-cyber/awesome-ai-pulse-georgia0 reactions
On the web · 11
- Oct 29, 2026Omniroute Review 2026: LLM Routing, Cost, Failover — swarm.beetlix.com
- Oct 20, 2026Run Claude Code for Free on Windows with OmniRoute and Google AI Studio (Gemini Flash) — dev.to
- Oct 19, 2026Benchmarking OmniRoute: Quota-Aware Fallback Latency and Token Compression Under Load — dev.tosays it tested it
- Oct 6, 2026How to Use Claude Code for Free with OmniRoute — dev.to
- Sep 23, 2026OmniRoute AI: Installation, Claude Code, Docker, and Troubleshooting — honestaireview.hashnode.dev
6 more on the web
- Sep 10, 2026Self-hosting OmniRoute with Docker Compose to structurally solve quota issues|株式会社ホコサキ — note.com
- Aug 5, 2026How to Give Claude Code 1.5 Billion Free Tokens a Month — mattpaige68.substack.com
- Jul 26, 2026How I Routed One Billion AI Tokens for $0 With OmniRoute — dev.to
- Jul 22, 2026I Call 250 Different AI APIs. This Gateway Gives Me One Endpoint Instead. — dev.to
- Jul 20, 2026OmniRoute Review (2026): Is the 20k-Star Free AI Gateway Worth It vs OpenRouter & LiteLLM? — dev.to
- Jul 5, 2026OmniRoute: Free AI Gateway with 231 LLM Providers (2026 Review) — andrew.ooo — andrew.ooo
Other versions1 project uses a version of this.
Word for word · 1
- diegosouzapw/OmniRoute★ 83k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository48 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- cli-a2aSkill
- cli-backup-syncSkill
- cli-batchesSkill
- cli-chatSkill
- cli-compressionSkill
- cli-contextsSkill
- cli-cost-usageSkill
- cli-evalSkill
- cli-healthSkill
- cli-keysSkill
- cli-mcpSkill
- cli-modelsSkill
- cli-plugins-skillsSkill
- cli-policy-auditSkill
- cli-providersSkill
- cli-resilienceSkill
- cli-routingSkill
- cli-serveSkill
- cli-setupSkill
- cli-skill-collectorSkill
- cli-tunnelSkill
- config-codex-cliSkill
- omni-agents-a2aSkill
- omni-api-keysSkill
- omni-authSkill
- omni-budgetSkill
- omni-cacheSkill
- omni-cli-toolsSkill
- omni-combos-routingSkill
- omni-compressionSkill
- omni-context-rtkSkill
- omni-db-backupsSkill
- omni-github-skillsSkill
- omni-inferenceSkill
- omni-mcpSkill
- omni-modelsSkill
- omni-providersSkill
- omni-proxiesSkill
- omni-resilienceSkill
- omni-settingsSkill
- omni-sync-cloudSkill
- omni-tunnelsSkill
- omni-usage-logsSkill
- omni-version-managerSkill
- omni-webhooksSkill
- ponytailSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

