The problem
"Tokenmaxxing — the biggest model on every call — buys accuracy by sacrificing cost & latency." POSTER
To hit accuracy, tokenmaxxing spends its way into one corner of the accuracy–cost–latency triangle — and the pull compounds from a single call to a full agent run. "One lever — more tokens — can't hold three constraints at once. A minor trade per call becomes a structural miss per run." DECK
Static routers
Pick one model up front, never adapts. POSTER
Per-call auto-switch
Switches per call, but never lets you set the cost / latency / accuracy balance for the whole workflow. POSTER
Split stack
AI gateway and AI observability are separate tools — pay for both and still hand-build the loop between them. POSTER
What is it
"Drop BitRouter into any loop — your models, your tools, your harness — then point it at your goal and it optimizes every call toward it." DECK
Built for two people on the poster: Will, a loop engineer who "lives in agentic coding loops — Claude Code, Cursor, Codex — all day," and Acme, a Series-A AI startup "running production agentic loops at scale." The docs put it plainly: an open-source, adaptive LLM gateway that runs as a single local binary, so "every step of every loop stops billing at frontier prices by default." POSTER WEB
What it does
Pick a point in the accuracy–cost–latency triangle; BitRouter routes every call to hold it there.
Goal-point routing
"You choose the balance… You set the point — BitRouter holds it, every run." DECK
Bring your own everything
Your harness (ACP, subagents), 100+ frontier and open models, your MCP tools and skills — "one agent loop · any topology." DECK
Routing as code
A declarative routing-policy.yaml — "version it, diff it, ship it. The loop reads it, then rewrites it." DECK
Reliability
Mid-run rerouting and automatic fallbacks keep "long loops alive through outages." WEB
Observability
Full tracing with cost attribution per run, exported over OTLP — in the path, nothing to bolt on. WEB DECK
Guardrails
Guardrails and rate limits "enforced once, at the router, for every agent." WEB
How it works
"Not a static router that decides once and rots — BitRouter runs a closed loop on every call, so it gets cheaper and sharper each lap with no tuning by you." DECK
Policy in
Routine work goes to open models; the hard calls escalate to frontier — the deck's example policy defaults to open/qwen3-coder, escalates past complexity 0.7 to frontier/claude-sonnet, and halts on spiral. DECK
Built with: Rust, Apache-2.0 (stated open source — the public repo checks out) · a single local binary · OTLP tracing · curated open-weight models: Qwen3, Llama, DeepSeek, Kimi K2, GPT-OSS. The poster's ecosystem tiles: DeepSeek, Qwen, Kimi, MiniMax, StepFun, Xiaomi MiMo, Z.ai, Tencent. POSTER DECK WEB
The numbers
The team's own benchmark and figures, as printed on their poster and deck.
The poster goes further: "SOTA on router benchmarks — beats closed-source routers like Droid Router & NotDiamond." Live checks: bitrouter/bitrouter is public — Rust, Apache-2.0, 211 stars, pushed 2026-07-22 — and a BitRouterAI/benchmarks dataset is public on Hugging Face (updated mid-July). The benchmark results themselves are the team's measurements. POSTER WEB Pending approval
Who's building it
Two co-founders, NYC / HK. Deck framing: "We are the routing layer we're building" — Chinese frontier labs as supply and origin, the global OSS community as demand and roots. DECK REGISTRY
Kelsen Liu
NYU — CS, Media & Business. Self-taught full-stack engineer. 3× consecutive ETHGlobal winner. — their deck's team slide.
Archer Yang
Zhejiang University — Aerospace. China NOI medalist. Rust China Conf speaker. Full-stack — ML, blockchain, embedded. — their deck's team slide.
Traction
"From self-improving LLM router to everything" — the deck's timeline, checked against what's live.
Gateway & observability
Their milestones: 3B+ monthly token usage, 2,000+ downloads, 200+ GitHub stars. Live: 211 stars, 13 forks on bitrouter/bitrouter, pushed 2026-07-22. DECK WEB Usage figures pending
The benchmark
"SOTA performance on Terminal-bench-2.1," routing traces open-sourced. The Hugging Face dataset BitRouterAI/benchmarks is live (updated mid-July; checked 07-22). DECK WEB
The org
19 public repos: harness integrations (OpenClaw, Hermes Agent, Pi Coding Agent), an elizaOS provider plugin, a Homebrew tap, and an open eval database of models and harnesses. WEB
The business: "Open source is the distribution — cloud is the business." Adopt at 0% markup (self-host free), a $20/mo retail-dev bundle of SOTA open-weight models, managed cloud and enterprise above it — "you pay list; we buy at a volume discount — the spread is our margin." Next on the timeline: an optimizer learned from every run's traces via distributed RL, then a full RL stack for personalized workflows. DECK
In their own words
How the team tells it — from their Mock Demo Day pitch, 2026-07-17, Kelsen Liu presenting.
"Everyone else routes the call. Only BitRouter turns routing, observability, evals and guardrails into one self-improving loop." The closing line of the deck's competition slide DECK
"In any agentic workflow in production it's cost, speed, or quality — how do you balance it is the problem we are trying to solve."
"We route each call to the model that fits, then we observe it, then we evaluate it — then our router learns the whole workflow and tunes the policy to optimize it."
"We benchmarked our router paired with GPT-5.5 on terminal bench 2.1 — 33% less cost without any performance loss. The control, purely GPT-5.5, is 77; ours is 76 at a third less cost."
"You can run any agents you use every day wrapped inside the TUI — at the bottom you see what a session costs — and let the optimizer agent observe and optimize the whole workflow for you."
Try it & links
Everything below was live-checked on 2026-07-22 unless marked otherwise.
| Surface | Where | Source |
|---|---|---|
| Website | bitrouter.ai — "A self-improving LLM router that optimizes agentic workflows with every run." | WEB Live · 07-22 |
| Docs | bitrouter.ai/docs — quickstart, models, routable primitives; core "open-source under Apache 2.0 and self-hostable for free" | WEB Live · 07-22 |
| GitHub | github.com/bitrouter/bitrouter — Rust · Apache-2.0 · 211 stars · pushed 07-22 | WEB Live · 07-22 |
| Benchmarks | huggingface.co/datasets/BitRouterAI/benchmarks — the deck's open-sourced traces | WEB Live · 07-22 |
| X | x.com/BitRouterAI — on the poster and linked from the site; direct fetch blocked 07-22 | POSTER REGISTRY Confirm live |
| Community | discord.gg/G3zVrZDa5C · founder call: cal.com/kelsenliu · linkedin.com/company/bitrouterai (registry; not live-checked) | DECK REGISTRY |
| Contact | kelsenliu@bitrouter.ai · archeryang@bitrouter.ai (poster) · contact@bitrouter.ai (site) | POSTER WEB Confirm preferred |
Provenance ledger
Every load-bearing claim and where it comes from; decisions live in §11.
| Claim | Comes from | Tier | Status |
|---|---|---|---|
| One-liner, tokenmaxxing framing, the closed loop, primitives | Cohort poster + demo-day deck, July 2026 | POSTER DECK | Team's own artifacts |
| Founders, roles, bios, NYC / HK | Poster team block + deck team slide; registry corroborates (2 members, NYC / HK) | POSTER REGISTRY | Corroborated |
| −33% cost per run on terminal-bench-2.1, quality held; Droid Router / NotDiamond comparison | Poster proof panel; deck; repeated in the mock pitch — team's own measurements, named third parties | POSTER | Pending approval |
| Deck traction chart (per-model bars) | Deck p9 — labeled "measured, not modeled" yet watermarked "placeholder data — for layout review"; bars not quoted here | DECK | Conflict — confirm |
| $0.026 example: −33% (poster) vs −80% vs all-frontier (site) | Poster policy.yaml panel vs bitrouter.ai, fetched 07-22 — same example, different baseline | POSTER WEB | Conflict — confirm |
| Repo facts (Rust, Apache-2.0, 211 stars, pushed 07-22, 19 org repos) | api.github.com, fetched 2026-07-22 — corroborates the deck's "200+ stars" | WEB | Verified live |
| 3B+ monthly tokens, 2,000+ downloads | Deck traction timeline — no public counter found to check | DECK | Pending approval |
| Benchmarks dataset public | huggingface.co/BitRouterAI — dataset "benchmarks," updated mid-July, fetched 07-22; contents not audited | WEB | Verified live |
| X handle @BitRouterAI | Poster, registry, and the site's footer; direct fetch returned an access wall 07-22 | POSTER REGISTRY | Confirm live |
| Earlier registry framing: "P2P LLM router," x402-kit, agentic-payments workshop | Cohort registry — records note the team repositioned around reliability + cost for coding agents; current poster/deck say "self-improving router" | REGISTRY | Confirm framing |
| Pitch excerpts (§08) | Mock Demo Day, 2026-07-17; lightly punctuated, two ASR garbles decoded (noted in tooltips) | PITCH | Pending approval |
Founder review
Five things before this page goes public.