mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-12 02:02:13 +03:00
81a37b67ed
OmniRoute v3.8.26 — see CHANGELOG.md [3.8.26] for the full notes. Highlights: Vertex AI media generation (#3929), GLM-5.2 effort-tier routing (#3885), sticky round-robin combos (#3846), OpenRouter connection presets (#3878), compression prompt-cache fix (#3936/#3890), and a security pass (form-data/vite + workflow hardening, #3949). Co-authored-by: artickc <artickc@users.noreply.github.com> Co-authored-by: rdself <rdself@users.noreply.github.com> Co-authored-by: herjarsa <herjarsa@users.noreply.github.com> Co-authored-by: Jack Smith <16862258+YunyunZhai@users.noreply.github.com> Co-authored-by: dhaern <dhaern@users.noreply.github.com> Co-authored-by: adivekar-utexas <adivekar-utexas@users.noreply.github.com> Co-authored-by: megamen32 <megamen32@users.noreply.github.com> Co-authored-by: zhiru <zhiru@users.noreply.github.com> Co-authored-by: insoln <insoln@users.noreply.github.com> Co-authored-by: diego-anselmo <diego-anselmo@users.noreply.github.com>
4.6 KiB
4.6 KiB
title, version, lastUpdated
| title | version | lastUpdated |
|---|---|---|
| OmniRoute vs Alternatives | 3.8.2 | 2026-05-15 |
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 | 207+ | ~100 | ~50 | ~30 |
| Self-hostable | ✅ | ✅ | ❌ | ⚠ paid |
| OAuth providers (Claude, Codex, Copilot, etc.) | 15+ | partial | ❌ | ❌ |
| Auto-fallback combos | 15 strategies | priority-based | tier-based | weighted |
| Tier 1/2/3 fallback (subscription→cheap→free) | ✅ + UI | manual | n/a | manual |
| Token compression | RTK (47 filters) + Caveman | none | none | none |
| Built-in MCP server | ✅ 87 tools, 30 scopes | ❌ | ❌ | ❌ |
| A2A protocol | ✅ 5 skills | ❌ | ❌ | ❌ |
| Memory (FTS5 + vector) | ✅ | ❌ | ❌ | ❌ |
| Guardrails (PII, injection, vision) | ✅ | partial | ❌ | ✅ paid |
| Cloud agent integrations | Codex, 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 | 42+ locales | ❌ | ❌ | ⚠ |
| Public agent skills (SKILL.md) | ✅ 10 | ❌ | ❌ | ❌ |
| 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 (207+)
- 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: 2026-05-15. Submit corrections via PR to keep this table accurate.