Five gh-aw releases this week (v0.91.4 to v0.91.8) add routing and ordered model fallback across Claude, Codex, and Pi, per-agent spend reporting, and Claude Code running on GitHub Copilot inference. v0.91.7 brings a native Go AGY engine and deprecates the Gemini engine in its favor, while v0.91.8 closes a custom grader sandbox escape.
A single policy proposes harness edits (prompts, tools, context, feedback handling) and reflects on their effect, and those runs then train its weights via SFT plus interleaved GRPO, reaching 82.1% on Polyglot and 48.3% on SWE bench Verified versus 62.6% and 41.0% for the best prior self evolution method. The harness loop alone lifted a GPT 5 mini agent from 24.4% to 48.3%, and the evolved harnesses transferred to other benchmarks without further tuning…
Claude Code's built in subagents stay on Anthropic models; this MIT plugin runs DeepSeek, Gemini (Antigravity), Codex, OpenCode, or Copilot as worker CLIs, each in an isolated git worktree with your verify command, then returns a short verdict and patch for Claude to review. Install with /plugin marketplace add rbinar/cli dispatch ; API keys stay in a local browser form and never pass through Claude…
Piotr Sarnacki found the agent built Rust and Elixir versions made different unprompted calls on backwards compatibility, Redis, and blocking database work, and the Rust one delivered about 1% of notifications under heavy load because of a 256 slot broadcast channel. Rerunning at a constant 100 POSTs/s, he argues dropping lagging clients beats Elixir's unbounded mailboxes, which reached 1.8GB and event delays near 180s…
Ted Haley's free MIT macOS tool indexes code, docs, and past Claude Code/Codex sessions on device and returns the few relevant passages over MCP, cutting lookup tool calls from 3.4 to 2.0 in their Claude Code benchmark. Apple Silicon, macOS 14+; pensieve integrate recommended wires Claude Code, Codex, Cursor, and other MCP clients…
The MIT Codex plugin and local MCP server create or attach Claude Code sessions, hand off scoped implementation in separate worktrees, then review and merge with independent frequency and reasoning knobs. It needs Codex CLI, a working Claude Code setup, Node.js 20+, and Git; Windows and macOS are supported, and Orca is optional…
Spotted something we missed? Start a thread.
