A high-performance, polyglot code-analysis graph for coding agents — cross-language, cross-process, and dynamic-dispatch edges that grep and LSP can't follow. 100% local, MCP-native.
5 files for Claude Code, Codex and OpenCode: add-lang, agent-eval, settings, OmniWeave AGENTS.md and 1 more — 14,225 tokens loaded in every session.
AGENTS.md A 7,113 tok CLAUDE.md A 7,112 tok .claude/settings.json A — .agents/skills/add-lang/SKILL.md A 79 tok .agents/skills/agent-eval/SKILL.md A 68 tok These files are SolvingLab/OmniWeave's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.