Daily · star velocity · 2026-06-05
A quiet Friday on GitHub: odysseus held the lead on June 5, 2026, but the day's tell was Anthropic shipping its own threat-modeling skills onto the board at #2.
Self-hosted AI workspace.
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
The agent that grows with you
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
An agentic skills framework & software development methodology that works.
An Open Source implementation of Notebook LM with more flexibility and features
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A quiet Friday at the top. odysseus held #1 with +142, well off the pace it would hit over the weekend. The day’s tell sits at #2: anthropics/defending-code-reference-harness (+61), Anthropic’s own skills for threat modeling and patching — the model vendor shipping onto the same board its users are crowding.
Below it, the cohort that has anchored the week: hermes-agent (#3), codegraph (#4), alibaba/open-code-review (#5) and headroom (#6) — agent tooling and code review, with no single breakout.
