Havuz

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

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven,

Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

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

Local-first agent workflow for building private cross-project memory with explicit consent, validation, and crash-safe history.

Your coding agent starts every session knowing nothing about your project. One line, and it writes its own memory from your real code, then

Build a reusable Markdown context about you and your company (Claude Code skills + templates), then use it in ChatGPT, Claude, Gemini, Curso

Data Wiki turns data into portable knowledge bundles following Open Knowledge Format (OKF) and serves them to AI agents over the Model Conte

《智能体工程：从一句话到一个闭环》（Prompt · Context · Harness · Loop），本书将大语言模型驱动的智能体系统拆解为四种递进的工程范式，四种范式从 Token 到 System，从一次调用到完整的自主闭环，构成了智能体系统的完整工程视图。

Engineering knowledge infrastructure for AI coding agents.

Loop Engineering — a skill for designing & reviewing autonomous/semi-autonomous agent loops (Claude Code, Codex, Copilot, Gemini).

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

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

Build micro-vertical AI products with memory, workflows, human approvals, and governed improvement. The open-source engine behind every Aree

Catch stale versions, broken paths, and missing scripts in your AI instruction files (CLAUDE.md, rules)

Template for creating a long-term sync hub that checks your company's data sources into Git as plain Markdown, giving AI coding agents durab

2 text files and a folder. The ICM Folder System I run several businesses on, in plain English, for people who do not write code.

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

Framework-agnostic, local-first memory lifecycle for AI agents: Rust CLI, SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve a

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers

aiduMEI⚕爱嘟优忆思——aidu Memory Engine Insight · 智能体通用智慧引擎——Excellent memory system for all agents.

Multiplayer harness where humans and AI agents work together and build on shared context.

Self-hosted evidence store for coding agents.

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

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,

Token-efficient Windows file discovery for Codex and AI agents using voidtools Everything (es.exe)

CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo)

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

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

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding a

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model,

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

Deterministic memory layer for your agents

Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.

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

Local-first, evidence-aware project memory for AI coding agents.

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

OMem (Office Memory) — local-first memory that automatically ingests your real work (mail, calendar, notes, files) from where it already liv

Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix commands. Zero API calls

Persistent, inspectable memory that grows and refines over time. Built on files. Owned by you.

Local-first, evidence-aware memory and project continuity for AI coding agents. Checkpoints, context packs and auditable receipts without te

A pure-Python reachability and skeletonization layer that decides what a coding agent actually sees before a request reaches the API.

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

CTX is the standard Cognitive Version Control System for AI. Structured working memory for AI agents. CTX preserves goals, tasks, evidence,

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop