Fetching from the wire…
Vibe Coding2026-09-25 · source-backed
332 points on Show HN September 24, 924 stars, MIT licensed, built on a vendored Code OSS fork. Claude Code, Codex or another agent gets an SDK to draw sequence and ER diagrams on a desktop canvas, and clicking a diagram element jumps to the underlying code through LSP navigation. (devdotfast/whiteboard) It also has a Rust AST-aware semantic diff that summarizes large added functions as pseudocode and collapses tests and docs, plus a decision log linking agent traces to the requirements you set. Reviewing an agent branch as a diagram plus a list of choices the agent made on its own is a review model I haven't tried, and I'd like to.
Each link below shares sources, entities, or timing with this story.
Warp released its client codebase under AGPL-3.0, surged to 56,000 GitHub stars and #2 on GitHub Trending. But the real story isn't the open-sourcing. It's the repositioning. Warp isn't calling itself a terminal anymore. It's an "agentic development environment." The product n...
v0.1.117, tagged August 28 one day after v0.1.116 and pushed again today, is an MIT-licensed Rust tool that turns Claude Code, Codex or OpenCode into research agents that propose an idea, change code, launch an experiment and inspect evidence in a loop. Each run gets an isolat...
A local-first observability dashboard that tails agent session files to show plans, tool calls, file changes and progress in real time across three different coding agents, MIT-licensed, still being pushed today (GitHub). It's the only repo carrying the agent-observability top...
affaan-m/ECC (36.3k forks, MIT) bundles 67 agents, 284 skills, 94 legacy command shims, and "instincts", patterns learned from prior sessions with confidence scores that auto-recall when relevant, plus a .ecc/memory/ markdown vault that's explicitly cross-harness, so context s...
msitarzewski/agency-agents added 446 stars today, packaging personas across "divisions" (frontend specialists, community experts, fact-checkers, reality checkers), each defined with a voice, a process, and concrete deliverables rather than a generic prompt template (GitHub). I...
Three frontier models shipped in a single week this month, and teams with a standing eval harness had a routing decision in hours. Anthropic's own agent-eval guidance says 20-50 tasks drawn from your real usage and real failures is enough to detect issues (DeepEval). DeepEval...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.