Havuz

Model-controlled context blocks for DeepSeek Harness PTC mode

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

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

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

Deterministic, bounded local Git context as Markdown or JSON. Standard-library Python CLI.

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

A high-performance, token-efficient Model Context Protocol (MCP) gateway proxy. Avoids context bloat and eliminates multi-turn tool discover

Small observability and context management extensions for the Pi coding agent

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

A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.

Claude Code's compaction engine, as a drop-in DeepAgents middleware

Cursor uses AI to edit code — we use AI to edit AI's context. 🪆 Context map + compression + version control for LLM context windows.

A skill for Antigravity that delegates scoped work to Gemini CLI or Codex CLI worker agents — keeping the main context clean.

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

A deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate con

Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, do

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clie

Branch-aware global context for AI coding tools — reusable context above the repo level for Codex, Claude Code, and multi-repo work.

Dynamic emotion system framework for Hermes Agent - real-time emotion detection,Long-term memory, context management, and recall systems, st

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

Local OpenAI/Anthropic-compatible proxy using structured conversation state to reduce repeated context. Savings and compatibility depend on

A single-file project management standard for agent-human collaboration. One markdown file captures everything about a project — from scopin

Autonomous session memory for Claude Code. Never lose context, never repeat yourself. AI-powered summaries, searchable history, and automati

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

Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.

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.

Help your agent understand your life, on your terms. Local photo clues, your explanations, reviewed context and read-only MCP. Experimental

Behavioral context engine for AI coding agents. Learns which code you actually need from git history, not just what's structurally connected

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

Agent Context Economy (ACE) LLM-first progressive source navigation for context-efficient AI coding workflows.

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

Codex long-task compaction continuity and subagent prompt configuration guide

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

MCP-compatible context and memory system: paged code navigation for AI assistants, plus a recorded, verified theory of what is known about t

Turn long AI conversations into reusable domain knowledge across sessions

I built Handoff to carry project decisions, failed approaches, test status, and next steps between coding sessions.

扫出并清除「自称已废」的墓碑 skill、AI 幽灵碎片与死代码，统计释放的 Token 与磁盘。· An agent skill that reaps tombstoned skills, agent leftovers and dead code, reporting tok

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

A Codex plugin and local MCP runtime for context-bounded image generation and inspection.

Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告，7种语言

Keeps AI assistants on track during long conversations by tracking tasks across sessions