breakwire-org/breakwire

Breakwire is a source-linked registry of changes that break AI agents: model retirements, API
deprecations, SDK breaking releases, MCP spec changes and security advisories. Send it an error, get back the claim
that explains it (e.g. AN-2026-0025) with the vendor's documented error string, affected versions, deadline, fix and
primary source.
This repo holds everything that talks to it:
| | Path | Install |
| TypeScript/JS client (zero deps, Node 18+, Workers) + Vercel AI SDK tools | packages/js | npm i breakwire |
| Python client (stdlib only, 3.9+) | packages/python | pip install breakwire |
| LangChain tools + callback handler | packages/langchain-breakwire | pip install langchain-breakwire |
| MCP server config for Claude, Cursor, VS Code, Cline, Codex, Windsurf, Gemini CLI | mcp/CLIENTS.md | https://breakwire.org/mcp |
| GitHub Action: fail CI on near deadlines / advisories | action (published as breakwire-org/breakwire-check) | uses: breakwire-org/breakwire-check@v1 |
| Framework snippets: Vercel AI SDK, OpenAI Agents, Anthropic SDK, LangChain, MCP TS client | snippets | |
## 30 seconds
bash
curl -s https://breakwire.org/api/lookup -H 'content-type: application/json' \
-d '{"error":"toolchoice: type \"tool\" and \"any\" are not supported for this model.","service":"anthropic-api"}'
ts
import { withBreakwire } from 'breakwire';
const create = withBreakwire((p) => anthropic.messages.create(p), { service: 'anthropic-api' });
try { await create(params) } catch (e) { console.log(e.breakwire?.id, e.breakwire?.fix); throw e }
python
from breakwire import withbreakwire
with withbreakwire(service="openai-api"):
client.responses.create(...) # exception gets .breakwire (id, fix, url) and a traceback note
## Principles
Opt-in and harmless. Lookups happen only on errors, are time-boxed, and never throw or replace your error.
Secrets stay home. Keys, tokens, emails, IPs, query strings and home paths are stripped in your process before
sending (shared test cases); the server redacts again.
No silent reporting. Outcome reports ("did the fix work") are sent only with autoReport/autoreport on, and
only after your retry actually ran.
Honest data. signature vs related confidence, explicit "not covered" for services without claims, and
community verification that has just started: most claims have no outcome reports yet, and each claim says so.