Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026
Showcase WeaveResults as reported by the project's author

Route between coding-agent models with the open-source Weave Router 2.0

The Weave team presented Weave Router 2.0 in a Show HN post. It is an open-source routing model that sits in front of coding agents and switches between LLMs per turn, and the authors say it matches the pass rate of a single frontier model at lower cost and with faster completion.

The problem

Coding agent sessions can involve around 100 LLM calls, and each call is a chance to pick a different model. Using one top model for everything is expensive, and switching models carelessly wastes money because each switch means filling a different prompt cache. The team wanted a router that could pick the right model per turn without exploring every possible path.

How they did it

  1. Plug the Weave Router into a coding agent harness such as Claude Code, Codex, OpenCode or Pi.
  2. Choose between self-hosting the open-source router from GitHub and the hosted version at weaveos.com/router.
  3. For self-hosting, supply provider access; OpenRouter is suggested as an easy start but is not required.
  4. Let the router send hard tasks such as tricky debugging to a strong model and simple frontend changes to a cheaper one.
  5. Optionally set a predefined budget, which the author confirmed is supported.

Results as reported by the project's author

  • As reported by the Weave author on Hacker News: on Terminal Bench 4.0 and SWE Atlas, the router had equivalent pass rates to GPT-6 Astra.
  • As reported by the author: on Terminal Bench the router cost 52% as much as Astra and completed tasks 2.2x faster.
  • As reported by the author: on SWE Atlas the router cost 54% as much as Astra and ran 2.5x faster.
  • The author credits a hidden Markov model plus classifier for bucket selection as the biggest gain, and cache-eviction impact estimation for most of the cost savings.

These figures are as reported by the project's author in Hacker News Show HN post by the Weave Router author ↗. AgentGid did not measure or independently verify them.

Takeaway. If you run coding agents at scale, a router that weighs model capability against the cost of switching caches may reduce spend without lowering pass rates, but test it on your own workloads since the figures are self-reported.
AgentGid's take

This suits developers or small teams already running a terminal coding agent with provider keys, and comfortable self-hosting a router or trying the hosted one. Watch the figures: the pass-rate and cost numbers come from the author, and your savings depend on provider pricing and your own task mix. Pi (Free, OSS) is a no-cost harness to pair it with, since you only pay the model provider.

The agents used here

Compare: Claude Code vs OpenAI Codex · Claude Code vs OpenCode · Claude Code vs Pi · OpenAI Codex vs OpenCode

Similar use cases

Showcase

Mod almost any PC game with Claude Code and the universal-modder plugin

An open-source GitHub project packages skills, a command-line tool, a shared knowledge base and the fal MCP server so AI coding agents such as Claude Code can mod PC games the use…

The repository ships three worked examples: a Terraria tModLoader weapon and boss pack with sprites made through fal, an Age of Empires II DE civiliz… (as reported by the project's author)

Claude CodeOpenAI CodexGemini CLIfal MCPCodexBuilding apps · Prototyping
Showcase

Let Claude Code and Codex point at Mac screen elements with bigarrow

An open-source, MIT-licensed macOS command-line tool called bigarrow, with a skill for Claude Code and Codex, lets AI agents draw a click-through arrow and text sign over the scre…

Drawing needs no macOS permission; only some target-finding modes need Accessibility or Screen Recording, granted to the terminal app that launched b… (as reported by the project's author)

Claude CodeOpenAI CodexCodexbigarrowInternal tools · Onboarding
ShowcaseOffrun

Run Claude Code and Codex agents in parallel on Mac with Offrun

Offrun is a free Mac app that runs coding agent CLIs such as Claude Code and Codex side by side, each in its own git worktree, using the user's own logins. The page is the product…

As reported by the Offrun site: each agent in a project works in its own git worktree, so two agents on the same repo do not touch the same files.

Claude CodeOpenAI CodexAntigravity CLIOffrunCodexCode review · Workflow automation

Guides