Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-09-15 · source-backed
An MIT gateway at 66,399 stars exposing one endpoint over 352 providers and 1,200+ models, with quota-aware auto-fallback and a compression layer claiming 15-95% token savings (GitHub). The PR-to-issue split is a contribution backlog rather than a bug backlog, consistent with the 550+ contributor claim. Pushed September 15 but the last tagged release, v3.8.50, is from August 26, so pinning a version puts you three weeks behind main.
Each link below shares sources, entities, or timing with this story.
diegosouzapw/OmniRoute added 1,343 stars on July 20, a single MIT-licensed gateway across 268+ providers (50+ free) and 500+ models including Claude, GPT, Gemini, Kimi K3, GLM and DeepSeek, wired for Claude Code, Codex, Cursor, Cline and Copilot. Quota-aware automatic fallback...
diegosouzapw/OmniRoute (44,768 stars, 833 today) is a free MIT gateway fronting 290+ providers and 500+ models for Claude Code, Codex, Cursor, and Cline. Today's commits include fix(antigravity): ban-safety hardening — bounded onboarding retries, gate thought-signature bypass...
Issue 6235 on anthropics/claude-code asks Claude Code to read AGENTS.md, the config file that Codex, Amp, Cursor and most other harnesses already load, rather than only CLAUDE.md. It has been open since August 2025. It has accumulated over 5,200 reactions and 300+ comments, ma...
Three things happened this month that only make sense together. Agent Plugins 1.0 shipped co-signed by six competitors: AWS, Anysphere, Microsoft, OpenAI, Vercel and Google (GitHub Changelog). It makes skills-plus-MCP bundles portable across clients. OpenAI's August 11 Codex c...
312 stars and 24 forks within 24 hours of appearing August 11, MIT (GitHub). Notable for targeting three harnesses at once, which puts it in the emerging agent-agnostic UI layer category rather than single-vendor plugin territory. One day old, no releases, no independent verif...
mikehasa/agentacct (547 stars, MIT, Python, pushed August 7) breaks each agent task into work steps: tools used, files changed, tests run, time and tokens spent, across Claude Code, Codex, OpenCode and others in a local-first dashboard. The no-telemetry positioning is the diff...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.