From e25251900d2c88d1d82697174af528c02a664401 Mon Sep 17 00:00:00 2001 From: Spikel Date: Sun, 7 Jun 2026 16:03:30 -0400 Subject: [PATCH] Add BitRouter to Runtimes, Harnesses & Reference Implementations Co-Authored-By: Claude Opus 4.8 (1M context) --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 96562b7..04b60c3 100644 --- a/README.md +++ b/README.md @@ -143,6 +143,7 @@ These benchmarks are especially useful when you want to compare harness quality, - [SWE-ReX](https://github.com/SWE-agent/SWE-ReX) - Sandboxed code execution infrastructure for AI agents, useful when harness work starts to merge into execution runtime design. - [AgentKit](https://github.com/inngest/agent-kit) - Inngest's TypeScript toolkit for building durable, workflow-aware agents on top of event-driven infrastructure. - [browser-use/browser-harness](https://github.com/browser-use/browser-harness) - A thin CDP-based browser harness that lets agents extend helper functions during execution, useful for inspecting self-healing web-task workflows. +- [BitRouter](https://github.com/bitrouter/bitrouter) - Agent-native Rust LLM router that optimizes your agent with every run: with zero harness changes, it makes every model call reliable, traceable, secure, and cost-effective. Fronts OpenAI, Anthropic, Google, OpenRouter, Bedrock, GitHub Copilot, and more behind one local endpoint, with cross-protocol routing, an MCP gateway, guardrails, observability, and multi-account failover. - [Citadel](https://github.com/SethGammon/Citadel) - A harness for Claude Code and OpenAI Codex with isolated worktrees, multi-agent coordination, and persisted memory and campaign state. - [Bring Your AI MCP](https://github.com/unitedideas/bringyour-mcp) - Public harness-migration reference for Claude Code to Codex moves, with installable auditor artifacts and explicit validation notes for hooks, MCP config, and instruction-file differences. - [Harbor](https://github.com/harbor-framework/harbor) - A generalized harness for evaluating and improving agents at scale, released alongside Terminal-Bench 2.0.