Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-07-30 · source-backed
Kritt-ai/open-kritt (created July 20, 456 stars, 93 forks, v1.2.0) is an AGPL-3.0 self-hosted platform that rejects the point-a-model-at-the-repo approach: it breaks security research into small focused tasks, fans them across Codex or Claude Code agents in parallel, then de-duplicates and ranks output under a consistent finding schema with custom severity rankers and post-script validation. The team publishes verifiable credentials, over $1,500,000 in bug-bounty payouts under the researcher name Blockian on Immunefi and HackenProof. Bring your own model.
Each link below shares sources, entities, or timing with this story.
elder-plinius/T3MP3ST (AGPL-3.0, created July 2, ~344 stars/day, 1,010 forks) is an offensive-security meta-harness running "keylessly" on coding agents you already subscribe to, with eight operators mapped to ATT&CK phases: Recon, Scanner, Exploiter, Infiltrator, Exfiltrator,...
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...
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...
QM went up under MIT license. Created July 29. As of the GitHub API check: 8,420 stars, 887 forks. Five days. YC uses it internally across accounting, legal, events, and engineering, including to build QM itself. Every employee and every Slack room gets its own scoped memory,...
yc-software/qm launched July 29 under MIT and is at 5,917 stars, 615 forks, 74 open issues: near 1,972 stars/day. Headless TypeScript/Fastify core on Postgres giving every person in an org an isolated sandbox with scoped memory, files and permissions, sharing work through Slac...
Intuition-Lab/personal-model (created July 10, 1,263 stars, v0.3.2) is a local-first long-term memory runtime that learns how you work from focused activity captured on macOS after you grant permission, then serves it to Claude Code, Codex, and Cursor Agent over MCP as a singl...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.