Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.
☆1,117Dec 3, 2025Updated 11 months ago
Alternatives and similar repositories for caveman-compression
Users that are interested in caveman-compression are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Plan, build and review software with your coding agents. Work side by side in the App or browser, or use your favourite terminal or IDE.☆2,135Updated this week
- 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.☆119,057Updated this week
- Chrome extension to enhance Google's AI Studio☆16Mar 20, 2025Updated last year
- 🌳 MCTS-inspired parallel beam search for conversation optimization. Explore multiple dialogue strategies simultaneously, stress-test a…☆35Jan 18, 2026Updated 9 months ago
- ☆18Jul 1, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies☆86,218Updated this week
- Self-hostable cloud coding agent based on Pi☆14Nov 1, 2026Updated last week
- Examples for using the SiLLM framework for training and running Large Language Models (LLMs) on Apple Silicon☆16May 8, 2025Updated last year
- Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cu…☆146,006Updated this week
- Baton coordinates coding agents. Each worker handles a focused task, and one orchestrator checks the result.☆17Sep 8, 2026Updated 2 months ago
- Clipboard API with text + image read/write/watch function for MacOS, Windows, Linux☆23May 28, 2026Updated 5 months ago
- 🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, bench…☆25,628Updated this week
- ☆17Jul 30, 2026Updated 3 months ago
- LLM-powered tooling for triaging the U.S. House Oversight & DOJ Epstein document release.☆34Sep 5, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for…☆79,359Updated this week
- Web based coding and computer use agent. Multi session. Voice chat. Browser use.☆23Updated this week
- The open-source app everyone uses to manage agents at work☆113,111Updated this week
- an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM☆56,460Updated this week
- Tmux session management toolkit for spawning and coordinating multiple AI coding agents across tiled panes☆13Sep 21, 2026Updated last month
- Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.☆188,906Oct 29, 2026Updated last week
- The open source coding agent.☆226,081Updated this week
- RouteWeaver: experimental cache-safe speculative inference and CPU/GPU transfer optimization for Qwen 27B on low-VRAM NVIDIA GPUs.☆35Oct 10, 2026Updated last month
- Pier Code is a terminal-native agentic coding tool that understands your codebase and helps you move faster by handling routine tasks, ex…☆17Aug 22, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI☆121,422Updated this week
- High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.☆18Mar 20, 2026Updated 7 months ago
- Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in c…☆33,874Updated this week
- aider is AI pair programming in your terminal☆50,066May 22, 2026Updated 5 months ago
- ☆15Jun 11, 2026Updated 5 months ago
- The best-benchmarked open-source AI memory system. And it's free.☆60,521Updated this week
- ☆10Mar 17, 2024Updated 2 years ago
- Skills for Real Engineers. Straight from my .agents directory.☆322,025Updated this week
- The agent that grows with you☆262,641Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆21Aug 11, 2026Updated 3 months ago
- Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https…☆6,182Updated this week
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.☆79,282Updated this week
- Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more☆40,281Updated this week
- Context7 Platform -- Up-to-date docs for AI agents☆64,603Updated this week
- Glamourous agentic coding for all 💘☆29,044Updated this week
- Advanced scheduler for Home Assistant: visual time blocks, weather rules, offline recall and a full Lovelace UI☆24Nov 2, 2026Updated last week
Are these results useful?