Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-08-09 · source-backed
Three long-lived repos repositioned their descriptions around agent-harness language while keeping their star history: zhayujie/CowAgent (created August 2022 as chatgpt-on-wechat, now 46,430 stars and 10,306 forks as an "open-source super AI assistant and Agent Harness"), mnfst/manifest (September 2022 as backend-as-a-service, now 7,415 stars under "Connect Your Agents And Harnesses With Any Provider"), and teaql/teaql-agent-kit (December 2018, now 2,803 stars as "a model-mediated harness for reliable agentic software development"). All three pushed within 48 hours. If you rank repos by stars when evaluating tools, note that accumulated stars from a prior product identity now sit on top of agent-era descriptions.
Each link below shares sources, entities, or timing with this story.
A GitHub repo cataloging Claude Code tips doesn't normally warrant a top story. But shanraisshan/claude-code-best-practice at 53.4K stars isn't a tips list anymore. It's the de facto reference for how an entire generation of developers is learning to work with AI coding agents...
DeerFlow (71K stars), CowAgent (45K stars), and BitFun independently landed on the same architecture: a lead/orchestrator agent that decomposes a task, spawns subagents in parallel, isolates execution in sandboxes, and coordinates via a message gateway plus shared memory and s...
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...
The AGPL-3.0 agentic video production system has 12 pipelines, 100+ tools and 700+ agent skill files turning a coding assistant into a video studio. Created March 29, now at 51,820 stars and 6,505 forks, but pushed_at is August 22 (GitHub Trending). Five days of star growth wi...
The changelog offers Z.ai's open-weights coding model with a 1M-token context free via Blackbox AI on AI Gateway, default for new eve agents, switchable for existing ones with eve set --model zai/glm-5.2. Excludes Fast mode and the glm-5.2-fast variant. Separately, Gemini 3.7...
Google shipped it August 13: FrontierCode 1.1 at 43.6% (from 34.4%), DeepSWE v1.1 at 65.3% (from 49.0%), WebDev Arena Elo 1588 (from 1538), AutomationBench enterprise workflow completion at 30.4% (from 17.0%). Introductory pricing is $0.75/M input and $3.75/M output through De...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.