A structured AI learning platform that guides people through planning, finding, explaining, testing, coaching, and recording knowledge. It supports project-based learning, exploring a subject, and learning for general understanding.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Replace a monolithic CLAUDE.md with a categorized memory/ directory that agents read on demand, so context is only spent on what's actually being worked on.
Initialize and maintain Claude Code project structures with adaptive project detection, CLAUDE.md quality scoring, and auto-sync documentation workflows.
★not rated 2
changed 5d agoA
tokens not measured
originalMIT
Make your AI agent get stronger with use — skill self-improvement, memory-skill feedback loops, and user profiling. Inspired by Hermes Agent's four-layer memory architecture.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Multi-agent fact verification for legal and financial documents. Extracts claims, verifies against web sources, cross-checks, and produces patched documents with citations.
Standard AI-dev setup: /factory-init stamps a repo with @claude workflows, plugin wiring, a marker-fenced CLAUDE.md, and a docs/memory/ index; /factory-update refreshes the standard parts. Ships shared skills (model routing, release flow, repo memory, CI agent ops), routed agents (implementer/reviewer/researcher), and.
★not rated 2
changed yesterdayA
tokens not measured
Corrective context for Zig that fixes Claude's outdated training data. Auto-detects whether the project targets 0.15.x or 0.16.x and injects the matching reference. Covers Writergate, the 0.16 Io interface, std.fs -> std.Io move, indexOf -> find rename, build.zig, format strings, ArrayList, BoundedArray…
★not rated 2 7d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: