Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-08-13 · source-backed
milind-soni/OpenMausBot (724 stars since August 11, Electron + React 19, MIT) makes each sidebar bot a real local Claude or Codex agent with its own personality, model, cloud computer, and connected apps, with approval gates. Distributes as a signed notarized one-click .dmg for Apple silicon. The README opens with a direct disclaimer that there's no token and no crypto affiliation, which tells you something about the current state of open-source agent projects.
Each link below shares sources, entities, or timing with this story.
CherryHQ/cherry-studio (50,068 stars) cut v2.0.0 on August 5 and reached 2.0.2 by August 7, rebuilding from chat client into a work surface with multi-window and split-view layouts. The release notes say the subscription part explicitly: OpenAI and Anthropic endpoints, reusing...
VoltAgent's awesome-design-md repository packages 57 complete brand design systems as structured markdown files. Apple, Notion, Airbnb, Stripe, Uber. Drop one in your Claude Code workspace and the agent generates pixel-accurate UI matching that brand's visual language. Source:...
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 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...
cristicretu/diri (217 stars, Rust, Apache-2.0, pushed August 7) runs multiple coding agents and shells concurrently across worktrees and remote hosts. Worktree isolation is the mechanism keeping parallel agents from clobbering each other's edits, and it's the correct primitive...
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.