Havuz

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

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

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

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

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

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

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

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。

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.

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

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

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

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

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

Safety-first GUI and CLI for auditing, backing up, importing, cleaning, and trimming Codex conversations without editing internal storage.

Minimal harness-agnostic recursive language model layer — one binary, Python + llm()

Claude Code 状态栏：会话花费、上下文占用、5h / 7d 限额预警，区分订阅制与按量付费。单文件 Python，零依赖。· A Claude Code statusline for session cost, context usage and limit warni

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

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

Lossless context folding for the Pi coding agent: only the oldest context changes; the fresh window stays untouched.

ripwire, coding agents için kod tabanını indeksleyip call graph, değişiklik etkisi ve ilgili testleri yerel bir CLI ve MCP server üzerinden sunar.

Neden yükseliyor · 60 günde 2.348 yıldız alması ve coding-agent araçlarına yönelik ilgi dikkat çekmesini açıklayabilir; ancak yükselişin doğrudan nedeni verilen verilerden doğrulanamıyor. Son 28 günde 2.779 commit yüksek aktivite gösterirken, yalnızca 2 farklı yazar görünmesi bu aktivitenin dar bir katkıcı grubunda toplandığını düşündürüyor.

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

Losslessly compress the tool output your AI agent sends the model, prove every value survived, and report the exact tokens removed. Run it a

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

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

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

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

Knowledge engineering for AI agents: distill corpora too big for any context window into small, verified, git-native knowledge bundles

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

Request-level image lifecycle middleware for AI coding agents: keep current-turn images, downgrade historical ones to stable placeholders.

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

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

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Oll

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and r

Local-first tool to visualize and analyze Claude Code, Cursor, Pi & OpenCode sessions — context tokens, LLM insights, governance artifacts.

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

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

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

Small observability and context management extensions for the Pi coding agent

See where your Claude Code tokens go — cost per call scales 4.3x with context size. Hooks + SQLite + dashboard + MCP server for context wind

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

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

contextzip CLI: zip the right parts of your codebase for ChatGPT, Claude or Gemini, then apply the AI’s changes back. Skips dependencies, re

Minimal Claude Code statusline — context window zones, rate limit countdowns, and git branch in your terminal

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

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

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

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

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