Developer Tools / AI Model Editing / Alignment Research

Senbonzakura

Open-source tool for removing refusal behavior from open-weight transformer language models by identifying and orthogonalizing refusal directions in activation space.

Clear26/30
Useful24/30
Specific17/20
Complete7/20
Senbonzakura screenshot

Why it was accepted

The page clearly describes an AI-related developer tool with a concrete purpose, usage instructions, supported model types, and implementation details. It shows enough evidence to be a useful public listing for AI builders and researchers.

Weakness

The snapshot does not show a working demo, screenshots, release history, or broader adoption signals. It also leaves some practical questions open, such as expected hardware requirements and how stable the results are across more models and seeds.

Review status

45 days ago #1760 ↓ -1

Last evaluated 45 days ago. Current rank #1760. Down 1 spot in the rankings.

Score history

74

Related listings

CodeGraph screenshot
94

Developer Tools / AI for Code

CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.

Traccia screenshot
#3 Traccia
92

Developer Tools / Code Assistant

Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.

scribe screenshot
#5 scribe
92

Developer Tools / AI Agents

Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.

LLMRender screenshot
92

Developer Tools / React Libraries

A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.