Tag
Headroom is an open-source tool that compresses tool outputs, logs, RAG snippets, and more read by AI Agents by 60-95% while maintaining answer quality, supporting reversible compression and cross-agent shared memory.
EarlyTom is a training-free framework that compresses visual tokens early in the vision encoder to reduce time-to-first-token and computational costs while maintaining accuracy, achieving up to 2.65x TTFT reduction.
LiteFrame introduces a highly efficient video encoder for Video LLMs that uses Compressed Token Distillation to enable up to 8x more frames and 35% latency reduction while maintaining accuracy, setting a new Pareto frontier for long-form video understanding.
OpenHuman is an open-source desktop AI agent from TinyHumans AI that uses a structured local memory pipeline instead of embedding-based retrieval. It has gained rapid traction with 20k+ GitHub stars and multiple Product Hunt leaderboard #1 rankings.
A skill/plugin for AI coding agents that reduces output tokens by ~75% by making agents communicate in a concise 'caveman' style while preserving technical accuracy. Supports multiple levels of compression and many agent platforms.
OmniRoute is a free, open-source AI gateway that connects to over 230 providers including 50+ free tiers, with intelligent routing and token compression to save costs. It serves as a unified endpoint for various AI tools like Claude Code, Cursor, and Copilot.