Fetching from the wire…
01
02
03
04
05
06
07
08
Vibe Coding2026-09-14 · source-backed
petergyang/no-ai-slop strips 20-plus patterns from any piece of writing, MIT, at 9,394 stars with 448 added today, and misbahsy/anti-ai-slop was posted to Show HN at 00:38 UTC as a four-stage gated skill for Codex or Claude Code. Both run the model's output back through a deterministic checklist after generation instead of prompting harder up front. If you have a house style, the gate-after-generation shape transfers even if the specific word lists don't.
Each link below shares sources, entities, or timing with this story.
A Chinese lab shipped a runtime that manages two American coding agents as subagents, and it went from repo creation to 145,439 stars in four days. deepseek-ai/deepseek-harness published dsh-v0.1.0-rc.7 at 12:01 UTC today, its first tagged release since the repo appeared on Au...
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...
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...
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...
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...
The model card went up at 02:17 UTC on September 10, MIT-licensed, multimodal MoE with a 1M-token context. The Causal Encoder-Decoder architecture projects the decoder's global KV cache from final encoder hidden states rather than per-layer, and SWA Bounded Replay cuts persist...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.