A method for steering llms to better follow instructions

A Unified Framework for High-Performance and Extensible LLM Steering

These are commands I use with agents, mostly Claude

bloom - evaluate any behavior immediately  🌸🌱

CIKM2023 Best Demo Paper Award. HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊

HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊 HugNLP will released to @HugAILab

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

An AI prompt optimizer for writing better prompts and getting better AI results.

❯ Lightweight, beautiful and user-friendly interactive prompts

A practical library of agents, instructions, and skills designed specifically for QA Automation Engineers, focusing on production-oriented solutions.

AI Context Kit provides a structured, instruction-based framework for context-aware AI collaboration across LLM providers. It includes authoritative specs, canonical templates, and skills workflows…

Context-Optimized Memory Bank — Reduce AI token usage with structured documentation and cache-aware reading strategies

CodeStory is a codebase grounding engine that preindexes code into a knowledge graph and enriches it with semantic context. Paired with coding agents, it results in fewer tokens, fewer tool calls, …

Context management for long-context LLMs, agents, and vibe coding. Instantly build context for an entire repo, selected files, folders, and GitHub issues to generate structured AI-XML context with …

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

Cursor uses AI to edit code — we use AI to edit AI's context. 🪆 Context map + compression + version control for LLM context windows.

Zed extension for Headroom — context compression for AI agents

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"

Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.

Compress tool outputs, logs, files, conversations, and RAG context before they reach the model. On measured workloads, Entroly reduces unnecessary tokens by up to 90% while preserving answer-critic…

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

AI agent memory using Modern Hopfield Networks — no LLM calls, no database, one matrix multiply. MCP server for Cursor, Claude Code, and other AI coding agents.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Must-read papers and blogs about parametric knowledge mechanism in LLMs.

[ACL '26] This is the code repo for our ACL '26 Findings paper "MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization"