Havuz

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent ca

Posthorse, Pi coding agent için eski context penceresini özetlemeden kapatıp çalışmaya kalıcı notlar ve geri alınabilir transcript ile devam etmeyi sağlayan bir extension'dır.

Neden yükseliyor · 27 günlük yaşına karşılık 248 yıldız ve son 28 günde 110 commit dikkat çekiyor. Bu, yoğun geliştirme ve ilgiye işaret ediyor; ancak yalnızca 3 farklı yazar bulunduğundan ilginin ve bakım yükünün ne kadar geniş bir topluluğa yayıldığı belirsiz. Yükselişin kesin nedeni verilen verilerden çıkarılamaz.

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

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive

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

Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.

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

🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.

An experiment-driven LLM engineering lab with 9 reproducible Python experiments exploring token economics, API costs, caching, context growt

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthrop

Terminal side pane for Claude Code that shows a session's agents as a live tree. Stop a running sub-agent, send it new instructions mid-task

✻ An animated HUD for Claude Code, with Claude's mascot: live context window, Max plan 5h/7d limits with pace forecast, cost, subagents and

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compr

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

Auto AI improver. Token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read hints, P

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx cont

Claude Code mod: context in tokens, 5-hour and weekly limits vs. the clock, prompt cache countdown, session cost and running agents, in one

A pure-Python system that automatically discovers, verifies, and applies relevant historical requirements for coding agents — no embeddings,

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre a

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

DeepSeek Harness 插件：一键匹配模型上下文窗口，展示容量来源，支持勾选批量配置、已有窗口管理和手动编辑。

A tool that replaces everything that can be deterministic in repository work: search, symbols, callers, task scope, history, review and Git

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Know your headroom. Context window usage bar for Claude Code.

A SillyTavern extension providing a multi-tier memory and narrative context system for AI roleplay. Tracks character facts, relationship his

Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside Deep

Session handoffs for Claude Code: skills that capture decisions, failed approaches and next steps, plus a Claude Code mod (/compact-handoff)

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

The agentic debugger for Claude Code, Codex CLI and Gemini CLI: a token usage, cost and context-window tracker that shows what the tokens AR

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pausel

Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows w

Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persiste

The context exoskeleton for AI development: optimize the entire development lifecycle to reduce token usage and context occupancy.

Persistent memory system for Coding Agents (Claude, Opencode, Codex), infinite context, learning extraction, persona modeling and so much m

Token-efficient facade and Codex skill for MCP for Unity: 96% smaller measured tool-schema surface, compact results, batching, and recovery.

Real-time statusline, live monitor, session analytics, and hooks for Claude Code

CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the con

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tokens

Claude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persist

Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git com

Proxy MCP: one server that runs Playwright, Figma, Chrome DevTools, Shopify Dev and Context7 behind a single connection - and cuts their tok