PythonView on GitHub
Heretic is a tool that removes censorship (aka "safety alignment") from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration" (Arditi et al. 2024, Lai 2025 (1, 2)), with a TPE-based parameter optimizer powered by Optuna. This approach enables Heretic to work completely automatically. Heretic finds high-quality abliteration parameters by co-minimizing the number of refusals and the KL divergence from the original model. This results in a decensored model that retains as much of the original model's intelligence as possible. Using Heretic does not require an understanding of transformer internals. In fact, anyone wh
You might also like
Other
warp
This is an issues-only repo for Warp where you can submit issues, bugs and feature requests. We built Warp to solve two problems we kept hitting as a team writing software: terminals haven't kept up with how developers work today, and agentic development tools don't scale beyond your laptop. Warp is a modern terminal built for coding with agents. Warp brings the terminal into the 21st century with modern UI and code editing features. Use Warp’s SOTA built-in agent Oz, or run CLI coding agents like Claude Code, Codex, or Gemini CLI.
Other
jcode
The next generation coding agent harness to raise the skill ceiling. Built for multi-session workflows, infinite customizability, and performance. Need Windows, Homebrew, source builds, provider setup, or tell your agent to set it up for you? Jump to detailed installation. jcode is built to be as performant and resource efficient as possible. Every metric is optimized to the bone, which is important for scaling multi-session workflows. Here we sample a few metrics to show the difference: RAM usage and boot up.
Other
financial services
Reference agents, skills, and data connectors for the financial-services workflows we see most — investment banking, equity research, private equity, and wealth management. Everything here is available two ways from one source: install it as a Claude Cowork plugin, or deploy it through the Claude Managed Agents API behind your own workflow engine. Same system prompt, same skills — you choose where it runs. Each agent is named for the workflow it runs. They're starting points: install the ones that match your work, then tune the prompts, skills, and connectors to how your firm does it.
Other
skills
Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or automating personal tasks. This repository contains skills that demonstrate what's possible with Claude's skills system. These skills range from creative applications (art, music, design) to technical tasks (testing web apps, MCP server generation) to enterprise workflows (communications, branding, etc.). Each skill is self-contained in its own folder with a SKILL.md file containing the instructions and metadata that Claude uses. Browse through these s