Keyword: context-compression
- @oh-my-pi/snapcompactReleased7h agoVersion16.2.5
Bitmap-frame context compression for vision-capable LLMs
- sigmapReleased4d agoVersion7.30.0
97% token reduction for AI coding. Extracts function & class signatures with TF-IDF ranking to feed only the right files to Claude, Cursor, Copilot, Aider, Windsurf, local LLMs & MCP. Zero dependencies, runs offline via npx.
- @prometheus-ai/snapcompactReleased6d agoVersion0.5.18
Bitmap-frame context compression for vision-capable LLMs
- knitbrainReleased3d agoVersion0.5.0
The local-first brain for coding agents: per-project memory, task-tier workflow routing, and lossless context compression — measured ~48% of all tool-result tokens on real sessions (60–70% on code/JSON/logs), answer-preservation gated, reproducible with o
- @pk-nerdsaver-ai/snapcompactReleased2d agoVersion16.1.11
Bitmap-frame context compression for vision-capable LLMs
- pi-smart-compactReleased2d agoVersion7.18.0
Verification-oriented smart compaction extension for Pi Coding Agent — deterministic extraction, exploration, synthesis, verification, metrics, and safety checks.
- @parad0x_labs/openclaw-context-capsuleReleased4d agoVersion1.6.0
Self-contained OpenClaw context engine that compresses older agent session history into a bounded extractive capsule, preserving decisions, tasks, errors, files, links, and durable facts while keeping recent messages verbatim.
- @raquezha/noheadroomReleased4d agoVersion0.3.0
Personal Headroom compression bridge for Pi with Docker-first defaults and Pi tool-name adaptation