mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-19 13:23:50 +03:00
Landed with the design call resolved per the owner's pick — **option 1**: the synced store is now endpoint-agnostic (persistDiscoveredModels and managedModelImport no longer drop non-chat models at write time), and chat selectability moved to read time (auto-pool expansion in autoStrategy applies filterChatSelectableModels; the models-route projection already had its chatOnly filter). Your discovery test now passes end-to-end (3/3): /api/show capabilities persist per connection and image/embedding requests route through the advertising host. Reconciliation notes: conflicted areas merged onto the current tip (adobe discovery import, requestedModel preflight signature, resolvedProvider fast-path coexists with the synced-route override — explicit resolution wins); carried base-red drains (#10055 memoization, #11071 test variants) dropped as already-landed; the managed-model-import exclusion test was propagated to the new contract (image/video models persist; the read filter still hides them from chat pickers — pinned by a new assertion). Full battery: 205/206 focused (the one red is a confirmed periodic-timer timing flake on the loaded devbox — 20/20 isolated), autoCombo vitest 30/30, combo suites 46/46, gates + typecheck clean. Thank you @yourspraveen — the capability probe + routing design was right; it just needed the store contract opened up. Fixes #11087.
5.6 KiB
5.6 KiB
title, version, lastUpdated
| title | version | lastUpdated |
|---|---|---|
| OmniRoute vs Alternatives | 3.8.50 | 2026-08-02 |
OmniRoute vs Alternatives
Objective feature comparison vs popular open-source AI routers.
Methodology: Public repos audited 2026-Q2. Versions as listed. Submit corrections via PR — we want this to be accurate.
| Feature | OmniRoute 3.8 | LiteLLM 1.x | OpenRouter (SaaS) | Portkey |
|---|---|---|---|---|
| Providers | 329 | ~100 | ~50 | ~30 |
| Free/no-auth catalog entries | 155 | n/a | passthrough | n/a |
| Self-hostable | ✅ | ✅ | ❌ | ⚠ paid |
| OAuth catalog entries | 23 | partial | ❌ | ❌ |
| Auto-fallback combos | 19 strategies | priority-based | tier-based | weighted |
| Fusion (parallel panel + judge synthesis) | ✅ | ❌ | ❌ | ❌ |
| Tier 1/2/3 fallback (subscription→cheap→free) | ✅ + UI | manual | n/a | manual |
| Token compression | 12-engine stack (RTK + Caveman + LLMLingua) | none | none | none |
| Multimodal generation (speech/music/video) | ✅ | ❌ | passthrough | ❌ |
| Built-in MCP server | ✅ 107 tools, 32 scopes | ❌ | ❌ | ❌ |
| A2A protocol | ✅ 6 skills | ❌ | ❌ | ❌ |
| Memory (FTS5 + vector) | ✅ | ❌ | ❌ | ❌ |
| Guardrails (PII, injection, vision) | ✅ | partial | ❌ | ✅ paid |
| Cloud agent integrations | Codex, Cursor, Devin, Jules | ❌ | ❌ | ❌ |
| Circuit breaker per provider | ✅ 3-state, lazy recovery | basic | ❌ | ✅ |
| TLS fingerprint stealth (JA3/JA4) | ✅ wreq-js | ❌ | ❌ | ❌ |
| Eval framework | ✅ built-in | ❌ | ❌ | ⚠ paid |
| MITM proxy (intercepts Cursor/Antigravity) | ✅ cross-platform | ❌ | ❌ | ❌ |
| CLI with system tray (no Electron) | ✅ | ❌ | n/a | n/a |
| CLI machine-ID auto-auth | ✅ | ❌ | n/a | n/a |
| Dashboard | Next.js 16 | basic | proprietary | proprietary |
| i18n | 43 locales | ❌ | ❌ | ⚠ |
| Public agent skills (SKILL.md) | ✅ 45 | ❌ | ❌ | ❌ |
| Tunnel support (Cloudflared, Tailscale, Ngrok) | ✅ | ❌ | n/a | n/a |
| License | MIT | MIT | proprietary | proprietary |
When to choose OmniRoute
- You self-host and want maximum provider coverage (329 providers, 155 free/no-auth catalog entries)
- You need a built-in MCP server (LLM tools, memory, skills exposed as tools)
- You need A2A protocol for agent-to-agent workflows
- You want fingerprint stealth (JA3/JA4) to avoid detection by upstream CAPTCHAs
- You need enterprise features (guardrails, evals, audit trail) without a SaaS bill
When to choose LiteLLM
- You're Python-first and need tight integration with
litellm.completion() - You need mature production deployment recipes (k8s, Helm charts)
- Your team already runs Python microservices
When to choose OpenRouter (SaaS)
- You don't want to self-host
- You're fine paying per-token at SaaS markup
- You need a single payment method across all providers
When to choose Portkey
- You need a commercial SLA with uptime guarantees
- You prefer a managed dashboard without ops overhead
- You need enterprise compliance features out of the box
Last updated: 2026-08-02. Submit corrections via PR to keep this table accurate.