Havuz

Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reco

天枢harness是一个的终端编程智能体，它要回答的核心问题是：模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环，不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境（CVM），把目标、状态、证据、资源、权限与终止条件从对话历史中外部化，由运行时持续管理。同

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

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

Model-controlled context blocks for DeepSeek Harness PTC mode

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

AI builder operating system. Turn Claude Code from a per-session tool into a workspace that remembers, maintains itself, and never goes stal

Claude Code mod: hands off to a fresh conversation when context fills up, keeps the cache warm while you're away, and turns what you teach C

Pensieve: never lose the thread. A local MCP server and Mac app that links your files, repos, agent sessions, tickets and messages into one

System One Coding Agents: code-level answers at the same score as Claude Fable 5.1 on the same 74-point xz benchmark (69 / 74, 93.2 % each),

AutoHarness: Automated Harness Engineering for AI Agents

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), def

A cache-aware attention and forgetting layer for high-frequency everyday AI chat.

Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sess

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts,

DSH 防退化套件｜不止打断，还会清创：把退化的思考块从模型可见历史里折叠掉，下一轮不再回传。复读分两型——A 型同一句死磕、B 型短句轮换（最难抓，实测英文 8 块全漏）。两个插件一套闭环，缺一个都会漏。

从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill

为 DeepSeek Harness 打造：选中 AI 回答或思考内容，随时追问、学习、检查与纠偏。

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, C

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already

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

The agentic workspace where people and agents work together in the loop.

A tested harness for durable work across coding agents: CLAUDE.md/CHECKPOINT.md state and 17 skills, a Claude Code plugin with enforcing hoo

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

🧠 布洛陀·五层记忆系统 v2.2.10 · 一包多平台：WorkBuddy·Qoder CN·ZCode·Hermes·Zwork(AutoClaw) 全自动｜豆包办公 一步粘贴｜LobsterAI 适配收尾中暂不推荐｜Trae Work/千问/TeleAgent 适配层保留待

Kanwas — Shared context board for teams and agents

Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and Open

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

CTX - Context Runtime Engine for Coding Agents

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no

Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.

🌀 MUSE — Memory-Unified Skills & Execution. A pure-Markdown OS for AI pair programming with lossless cross-conversation context management.

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

Plan, build, review, and ship to the real world. Full opinionated harness with built-in Project Management and DevSecOps to code and maintai

Beastmode: MofA (Mixture of Agents) orchestration framework for Hermes/OpenClaw/Codex with MemroOS-style context continuity.

Open-source, model-portable coding agent built for cost-efficient, verifiable software work—with model routing, progressive context, compact

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD met

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

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local proj

Local context manager for Claude Code and Codex with workstreams, transcript binding, and branching.

面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent handof

Re-anchor long conversations that drift through repeated local corrections.

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants