context-compression repositories

Trending repositories tagged context-compression, ranked by trending score. Updated daily.

  1. 1
    snap-stanford/memorilla

    🦍 Memorilla: Latent Semantic Memory for LLMs

    GitHub · Python · 1,283 stars · 85 forks · 0 stars in 24 hours · Trending score 2.11

  2. 2
    HoangP8/tokless

    An effective and efficient coding-agent setup in under 30 seconds: best tools, unified instructions, any OS.

    GitHub · Go · 384 stars · 38 forks · +1 stars in 24 hours · Trending score 0.97

  3. 3
    anthony-chaudhary/fak

    Agentic Runtime

    GitHub · Go · 50 stars · 16 forks · +1 stars in 24 hours · Trending score 0.78

  4. 4
    ojuschugh1/sqz

    Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

    GitHub · Rust · 678 stars · 43 forks · 0 stars in 24 hours · Trending score 0.63

  5. 5
    JustVugg/flint

    Help AI agents use fewer tokens and keep more useful context. Reversible code, JSON and text compression, persistent memory, focused reads and version-aware edits.

    GitHub · Python · 15 stars · 2 forks · 0 stars in 24 hours · Trending score 0.42

  6. 6
    fajarhide/contexere

    The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

    GitHub · Rust · 379 stars · 37 forks · 0 stars in 24 hours · Trending score 0.41

  7. 7
    juyterman1000/entroly

    Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

    GitHub · Python · 488 stars · 74 forks · 0 stars in 24 hours · Trending score 0.37

  8. 8
    Adityapal67/context-graph-compressor

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

    GitHub · 37 stars · 9 forks · 0 stars in 24 hours · Trending score 0.32

  9. 9
    activeing123/mcptoon

    One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 561KB, pure Python. | 零依赖 CLI:管所有 MCP 工具与技能,工具发现省 99.2% token。

    GitHub · Python · 431 stars · 26 forks · 0 stars in 24 hours · Trending score 0.29

  10. 10
    manjughosa/magpie-compress-core

    magpie 网关的上下文压缩插件:16 个策略、四档预设、独立页面与面板

    GitHub · JavaScript · 10 stars · 3 forks · 0 stars in 24 hours · Trending score 0.28

  11. 11
    khanhtq29vn/contextcraft

    AST-Aware, Personalized-PageRank-Ranked, Token-Budgeted Codebase Compressor for LLMs

    GitHub · Rust · 65 stars · 7 forks · 0 stars in 24 hours · Trending score 0.10

  12. 12
    Avazbek22/DevProjex

    Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.

    GitHub · C# · 41 stars · 8 forks · 0 stars in 24 hours · Trending score 0.10

  13. 13
    ZipengWu365/TOMC

    TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.

    GitHub · Python · 264 stars · 26 forks · 0 stars in 24 hours · Trending score 0.10

  14. 14
    yoza10635/dsh-argp

    dsh 的上下文压缩插件:工具结果按实体标签确定性剪枝(0 LLM),对话正文只在压缩事务内 LLM 摘要,剪掉的原文可按标签逐字召回,必超窗的请求先压后发。 Context compaction plugin for dsh (DeepSeek Harness): deterministic entity-label pruning of tool results (0 LLM), LLM prose summaries only inside compaction transactions, verbatim recall of pruned text by label, over-window requests compacted before sending.

    GitHub · TypeScript · 15 stars · 2 forks · 0 stars in 24 hours · Trending score 0.09

  15. 15
    lucasmartins-ai/lcc

    Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claude Code plugin. MIT.

    GitHub · Python · 20 stars · 6 forks · 0 stars in 24 hours · Trending score 0.09

  16. 16
    getappz/agentflare

    Run AI coding agents efficiently, and coordinate more than one of them. Zero fluff, zero runtime deps.

    GitHub · Rust · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09

  17. 17
    dshakes/distil

    Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.

    GitHub · Python · 21 stars · 3 forks · 0 stars in 24 hours · Trending score 0.07

  18. 18
    RAKKUNN/vicem

    Zero-dependency AI agent context baton & diet suite. Hand off sessions between Claude Code, Codex, Gemini, and Cursor with 80% fewer tokens.

    GitHub · JavaScript · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.05

  19. 19
    condense-chat/dense

    Open-source CLI for running Claude Code, Codex, and OpenCode through Condense. Compress repeated context and see token savings per session.

    GitHub · Rust · 16 stars · 1 forks · 0 stars in 24 hours · Trending score 0.05

  20. 20
    avtc/avtc-pi-session-owl

    Background-maintained append-only knowledge graph; roots become the compaction summary; the agent traverses and regex-searches it to recall messages, tool calls, own thinking. For pi and Claude Code

    GitHub · TypeScript · 8 stars · 1 forks · 0 stars in 24 hours · Trending score 0.03

  21. 21
    zhibaiYingChuan/LRC

    为 AI 记忆提供了一种从“容器”到“场”的范式迁移,实现永久记忆。

    GitHub · Rust · 44 stars · 9 forks · 0 stars in 24 hours · Trending score 0.02

  22. 22
    alpertarhan/pi-smart-compact

    Smart Compact — recoverable context cleanup, verified compaction, session navigation and project memory for Pi Coding Agent.

    GitHub · TypeScript · 38 stars · 9 forks · 0 stars in 24 hours · Trending score 0.00

  23. 23
    DJLougen/hive

    CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~45% lower cost. Glues busyBee-cpu, honey-comb, and rust-brain.

    GitHub · Python · 40 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  24. 24
    Thanatos9404/llmslim

    Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

    GitHub · Python · 27 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00