Havuz

GatherThread 共序：本地 AI 编程 Agent 多人联机协作、实时共享上下文。Self-hostable collaboration for local AI coding agents, Codex Desktop connector & DeepSeek Har

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,

Halofy, organizasyonel bilgiyi AI agents ile paylasirken identity, access control, provenance ve audit kurallarini tek bir katmanda yoneten bir yazilimdir.

Neden yükseliyor · 36 gunde 335 yildiz, projeye erken ilgi oldugunu gosteriyor; ancak ilginin nedenini olcumlerden belirlemek mumkun degil. Son 28 gunde commit ve farkli yazar sayisi sifir oldugundan, bu ilgi guncel gelistirme temposuyla desteklenmiyor.

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.

Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have

Production-Stage Visual Design & In-Codebase UI Engineering Suite

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

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

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

⚡ TidyFactor Architecture Ecosystem , AI-Native Web Architecture, Design Systems & Agent Skills .

MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker quick start for enterprise agen

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

A Codex skill for durable project memory across context compaction

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.

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

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

AI Context Linker is a privacy-first context compiler. Turn local project context into reviewable Markdown for ChatGPT planning and Codex de

Finds the claims in your CLAUDE.md / AGENTS.md / skills that your code no longer supports. Zero-config, no API key.

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

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

A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first M

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

Persistent coding intelligence for Codex — project-aware context, adaptive reasoning, scoped changes, and risk-aware verification.

Token-budgeted codebase discovery for agent shells and Pi: cross-language maps, focused navigation, and impact analysis.

让 Codex 少烧 Token、少造复杂度，同时不降智的代码约束 Skill

Инженерный skill для проектирования, реализации, отладки и оценки AI-агентов в Codex и Claude Code по книге Bojie Li.

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

Deterministic memory layer for your agents

The open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery f

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

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

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.

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.

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across ses

Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local S

Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface o

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

Turn long AI conversations into reusable domain knowledge across sessions

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

Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.

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

Wordcell keeps decisions, plans, and sources as Markdown beside your code, so coding agents can find them from the file they are about to ch

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

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 open memory layer for collective agent awareness — a vendor-neutral MCP service for shared AI-agent memory.

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

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

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Workflow-agnostic guardrails for AI coding agents: spec sync + risk-triggered engineering discipline for Claude Code and Codex.

The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents an