Havuz

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

One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 ->

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

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

🦍 Memorilla: Latent Semantic Memory for LLMs

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, C

面向 AI Agent 的高并发、低延迟上下文治理与 Prompt Cache 守护网关 (Tree-sitter AST / Tool Delta / 50%~80% Token 削减)

Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt

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.

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

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

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

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

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

Agentic Runtime

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summa

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 ne

Zed extension for Headroom — context compression for AI agents

铃音的记忆写入协议 - an informatics protocol: fragmented, cue-based, symbolic, highly compressed information for AI agents; usable for memory writing

Cursor uses AI to edit code — we use AI to edit AI's context. 🪆 Context map + compression + version control for LLM context windows.

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflo

Cost-efficient coding-agent runtime: prefix-aware prompt-cache routing, poisoning-safe semantic cache, budgeted context compression, request

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

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

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line

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

Staged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scori

Context compression for MCP. Same upstream call, exact results recoverable.