Maintainer of this skill?
Automated security scan — not a certification.
by bitrouter
The minimal interpretable model router that learns & adapts to your agent workflows
# Add to your Claude Code skills
git clone https://github.com/bitrouter/bitrouterLast scanned: 6/5/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-06-05T08:07:54.884Z",
"npmAuditRan": true,
"pipAuditRan": true
}See how bitrouter compares with popular alternatives.
bitrouter is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by bitrouter. The minimal interpretable model router that learns & adapts to your agent workflows. It has 235 GitHub stars.
Yes. bitrouter passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/bitrouter/bitrouter" and add it to your Claude Code skills directory (see the Installation section above).
bitrouter is primarily written in Rust. It is open-source under bitrouter on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh bitrouter against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
The minimal interpretable model router that learns & adapts to your agent workflows.
Point any OpenAI-compatible agent at your local BitRouter instance, choose bitrouter/auto, and keep working.
- OPENAI_BASE_URL=https://api.openai.com/v1
+ OPENAI_BASE_URL=http://localhost:4356/v1
Then set the request model to:
bitrouter/auto
BitRouter runs locally and exposes an OpenAI-compatible API, so existing agents and tools can switch over with minimal changes.
You can also give your coding agent the /bitrouter skill to install, configure, migrate to, and troubleshoot BitRouter for you:
npx skills add bitrouter/bitrouter
Try BitRouter Cloud →: Don’t want to run the router locally? Use
https://api.bitrouter.ai/v1as your base URL instead.
One Rust router sits between your agents and every model provider. Extend it with providers, routing policies, tools, skills, and sub-agents without rebuilding your workflow around a new agent runtime.
Routing policy lives in files you own. Routes are inspectable, changes are diffable, and a live policy changes only when you explicitly publish it.
Start with bitrouter/auto, then shape the models, rules, guardrails, and
evaluation objective around your own loop. BitRouter learns from the outcomes
you admit and proposes a new policy you can review, publish, or revert.
Keep the clients and workflows you already use:
bro code, native launchers, and ACP adapters.On Terminal-Bench 2.1, BitRouter cut API cost by 40.9% while achieving nearly the same reward as using gpt-5.6-sol alone.
| Configuration | Reward | Cost / trial | Cost savings |
|---|---|---|---|
gpt-5.6-sol only |
81.56% | $0.830 | — |
| BitRouter | 81.25% | $0.490 | 40.9% |
| Random model mix | 76.50% | $0.553 | 33.4% |
BitRouter dynamically routed between GPT-5.6, Kimi K3, and DeepSeek V4 Flash, retaining nearly all of GPT-5.6’s task performance while substantially reducing model cost.
The random baseline used the same model mix, showing that the savings come from routing decisions—not simply using cheaper models.
Results use the strict 80-task common-valid set and frozen API prices. This is a research benchmark, not an official Terminal-Bench submission.
See the full study and limitations and the BitRouterAI/benchmarks dataset for reproducible results.
# macOS / Linux
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/bitrouter/bitrouter/releases/download/v1.0.0-alpha.33/bitrouter-installer.sh | sh
# Homebrew
brew install bitrouter/tap/bitrouter
# Windows
powershell -ExecutionPolicy Bypass -Command "irm https://github.com/bitrouter/bitrouter/releases/download/v1.0.0-alpha.33/bitrouter-installer.ps1 | iex"
# npm
npm install -g bitrouter
# From source (Cargo)
cargo install bitrouter
bro code (aka. BitRouter Orchestrator) is BitRouter's CLI workspace for coding-agent conversations. On the
first run, bro guides you through setup and opens the default agent. Use
bro code directly for a BRO conversation or to reopen a durable Thread.
Use bro code <agent> for an explicit ACP harness.
bro # first-run setup, then the default agent
bro code # BRO conversation; ← browses durable Threads
bro code codex # start an interactive Codex ACP session
bro code claude # start an interactive Claude ACP session
bro run claude "summarize this repo" # run one headless agent turn
BitRouter discovers a compatible local coding-agent CLI automatically. Its
built-in Codex and Claude adapters require Node.js 22+ and npx; when the local
CLI is unavailable, the adapter uses its bundled worker.
Use the surrounding bro commands to inspect and control the router while you
work:
bro requests # settled requests and spend
bro route <model> # explain how a model name resolves
bro start # start the local router
bro stop # stop the local router
bro restart # restart the local router
bro init # scaffold advanced routing configuration
bro claude and bro codex launch each harness's native interface with
per-process BitRouter overrides. bro code <agent> keeps the conversation
inside BitRouter's interface; bro run <agent> is the headless equivalent.
See docs/CLI.md for the complete command reference, session
controls, flags, and config resolution.
Ready-made policy specs for common agentic workflows start in templates/auto-router/: a predictive bitrouter/auto / bitrouter/auto:cost ladder using GPT-5.6 as the strong tier, Kimi K3 as balanced, and DeepSeek V4 Pro as economy. Treat it as a starting point and evaluate it against your own loop before publishing a live policy.
BitRouter routes to a model, not a provider. Each model below is served by many providers — its own lab, hyperscalers (AWS Bedrock, Alibaba Cloud), gateways (OpenRouter, OpenCode), and serverless clouds — and BitRouter picks the cheapest route per call. The bars are those routes: the more providers serve a model, the more room the router has to move.
Bring your own key to any of them, or use one BitRouter Cloud account with no keys at all. Frontier models from OpenAI, Anthropic, Google, and xAI also route over a subscription sign-in (Claude Pro/Max, GitHub Copilot, ChatGPT Codex) instead of a key.
The chart is generated from dist/registry/ on every catalog
change — it is never hand-maintained, so it cannot drift from what the router
actually resolves. Full catalog in registry/.
Try BitRouter Cloud → or reach out directly:
Want a first-party provider integration, or building an open-source agent/harness? Email kelsenliu@bitrouter.ai or book a meeting — open-source builders get up to 50% off for you and your community.
docs/DEVELOPMENT.md — workspace architecture and SDK internalsCONTRIBUTING.md — contribution workflow, issue reporting, and provider updatesCLAUDE.md — guidance for AI coding agents working in this repositoryskills/ — the /bitrouter Agent Skill (source of truth)