Skip to content

Add claude-distill: first-principles memory, A/B tested (+6pts vs vanilla) #280

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tomacco wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add claude-distill: first-principles memory, A/B tested (+6pts vs vanilla) #280

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,7 @@ A curated list of awesome tools, skills, plugins, integrations, extensions, fram
- [**claude-code-semantic-memory**](https://github.com/gtrusler/claude-code-heavy) (70 ⭐) - Persistent semantic memory system for Claude Code.
- [**Agent-Fusion**](https://github.com/krokozyab/Agent-Fusion) (46 ⭐) - A multi-agent orchestration system that enables Claude Code, Codex CLI, Amazon Q Developer, and Gemini Code Assist to collaborate bidirectionally through intelligent task routing and consensus-based decision making.
- [**Severance**](https://github.com/blas0/Severance) (41 ⭐) - A semantic memory system designed for Claude Code.
- [**claude-distill**](https://github.com/tomacco/claude-distill) — First-principles memory for Claude Code. Encodes corrections as reusable principles (not flat facts), retrieves by relevance via native rules/, and pushes back when you repeat a mistake it already learned. A/B tested: +6 points vs vanilla Claude on a 12-point scale. Zero dependencies — 18 lines of config.
- [**AgentCheck**](https://github.com/devlyai/AgentCheck) (33 ⭐) - Local AI-powered code review agents for Claude Code.
- [**claude-agents**](https://github.com/tddworks/claude-agents) (14 ⭐) - A collection of specialized AI agents for Claude Code that enhance software development workflows with focused expertise in specific domains.

Expand Down