#Context-compression

Showing 11 of 11 repositories tagged #context-compression, ranked by stars

open-compress
open-compress
claw-compactor

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

Score
100
★ 2.2k ⑂ 209 +5/day
Python
manojmallick
manojmallick
sigmap

97% token reduction for AI coding sessions — zero deps, 31 languages, MCP server

Score
83
★ 590 ⑂ 39
JavaScript
juyterman1000
juyterman1000
entroly

Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding. Local proxy that compresses context, keeps provider caches hot, and verifies LLM output ($0 hallucination guard). Drop-in for Cursor, Claude Code, Codex, Aider + 34 more and custom providers — 30s, no code changes

Score
67
★ 419 ⑂ 66
Python
LearnPrompt
LearnPrompt
cc-harness-skills

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

Score
50
★ 221 ⑂ 63 +1/day
Python
borhen68
borhen68
TokenTamer

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

Score
33
★ 123 ⑂ 20 +1/day
Python
HoangP8
HoangP8
tokless

A unified CLI to install and update token-saving plugins — RTK, Caveman, CodeGraph, and Context-Mode — for Claude Code, OpenCode, Codex, and Antigravity. Minimal setup. Any OS.

Score
17
★ 107 ⑂ 10 +19/day
Go
castnettech
castnettech
mnemosyne

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

Score
0
★ 58 ⑂ 9
Python
Madhan230205
Madhan230205
token-reducer

⚡ 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.

Score
33
★ 38 ⑂ 3 +7/day
Python
agiwhitelist
agiwhitelist
tokdiet

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Meters every token + USD cost, compacts bloated context to cut pay-per-token API spend, and runs shadow-eval to prove quality held. ccusage-style metering + live local dashboard.

Score
67
★ 37 ⑂ 2
TypeScript
Adityapal67
Adityapal67
context-graph-compressor

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

Score
100
★ 33 ⑂ 9
RainCherb
RainCherb
context-diamond

Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.

Score
0
★ 19 ⑂ 0
Python
Related Topics
#llm#developer-tools#python#ai#mcp#claude-code#token-optimization#llm-tools#cli#openai#ai-agents#anthropic

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly