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.

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

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

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

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

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),

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

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

AutoHarness: Automated Harness Engineering for AI Agents

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

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

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

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

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。

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

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

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

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

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

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。

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

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

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

AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean

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

CTX - Context Runtime Engine for Coding Agents

Self-hosted AI workspace built around context management. Works solo, scales to teams.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code:

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

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Sess

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

Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team co

A visual, editable context management panel for Codex. Better context compression, smarter compression strategies, automatic context organiz

Smarter context for Claude Code — semantic rule injection that learns what you need

ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server

🧠 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

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

Humanlike — deterministic persona, context, memory and privacy controls for conversational AI agents · Детерминированное поведение ИИ-агенто

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

The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing tha

Kanwas — Shared context board for teams and agents

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

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

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

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

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