Havuz

CLI and a Chrome Extension designed for you to review AI generated code locally and on GitHub PRs

Use Codex, GLM, and other coding agents as Claude Code subagents.

⚡ A native app for controlling your coding agents.

A lightweight, zero-dependency Python checkpoint layer for structured LLM output reliability.

Fast large-file log & JSONL viewer for Windows — 1 GiB indexed in 92 ms, regex search in 115 ms. 丹青日志 · Windows 大文件日志/JSONL 查看分析器 (Rust)

Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become perman

Swarm intelligence for distributed AI agents. One agent learns, the whole swarm knows. Shared memories, reminders and agent-to-agent message

A desktop coding workspace for AI agents — chat, files, editor, terminal, Git worktrees and browser preview, plus bounded, evidence-driven R

Define your SDLC as a graph and run every change through it on Claude Code, Codex, and your own agents.

Claude Code mod that draws Edit and Write diffs in two side-by-side columns

Memory for coding agents that checks itself against your code. Every memory carries evidence; stale facts never reach the context.

Tizen development skills & plugins for AI coding agents: install the Tizen SDK, create, build, debug and test Tizen Web, Native, .NET, RPK a

Generate interactive API documentation and typed Python SDKs from any OpenAPI specification

Create Comic with Plan anywhere. Render anywhere. Resume everywhere.

Local-first Codex 5-hour window scheduler for Windows and Linux. Plan when your reset clock starts with a minimal guarded request, without a

JevGrep, coding agents’ın bir davranışın kodda nerede gerçekleştiğini doğal dil sorgularıyla bulmasına ve ilgili kaynak parçalarını satır numaralarıyla almasına yardımcı olur.

Neden yükseliyor · 8 günlük repoda 81 yıldız dikkat çekici bir erken ilgiye işaret ediyor; son 28 günde görülen 107 commit de yoğun geliştirme olduğunu gösteriyor. Ancak yalnızca 2 farklı yazar var ve bu veriler ilginin nedenini ya da sürdürülebilirliğini tek başına kanıtlamıyor.

Claude Code ve Codex geçmişindeki tekrarlanan istekleri bulup proje içinde kullanılabilir kısa agent komutlarına dönüştüren bir Agent Skill.

Neden yükseliyor · Agent araçları arasında tekrar kullanılabilir iş akışlarına ilgi çekiyor olabilir; ancak yükselişin nedenini doğrulayacak bağımsız kanıt yok. 9 günlük yaşında 104 yıldız ve son 28 günde 17 commit başlangıç ilgisi ve hareketlilik gösteriyor; 2 farklı yazarla proje henüz küçük ölçekli.

The IDE built for AI coding agents.

Version control for AI agents — track what your agent did, blame any line to a prompt, inspect any step.

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

lowfat - slim your command output. strips noise, saves tokens.

ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.

An infinite canvas desktop app for visually managing terminals

Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with

Token telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude

The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

macOS desktop widget for OpenAI Codex usage, quota tracking, token usage, and today task board

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

Mine your Claude Code and Codex logs into a local you.md agent profile.

Proper sandboxing for agentic coding and web browsing

A live database structure viewer for Laravel that renders your schema as a scrollable, zoomable ER diagram. Structure only, never data.

Claude Code plugins for the work that keeps coming back: repo maps, conditional rules, ticketed parallel work, extra subscription models, lo

Search WeChat public account articles by keyword via Sogou WeChat Search. Returns structured JSON — no API key required.

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud,

A customizable terminal splash screen with plugin-based data sources.

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, browser tools, OpenAI/Anthropic-c

Intensity slider from tipsy (0.1) to blackout (1.0). 5 moods, 8 creative techniques. Lowers inhibition, not intelligence. Unfiltered genius

Component layer for AI agents: implementation-aware contracts for building project-native interface components.

OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles th

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

A persistent incremental diff review loop for pi

A local emulator of the Scaleway, Outscale and Exoscale APIs. Their own official CLIs drive it end to end, Terraform and OpenTofu drive two

Vibe Island — macOS notch panel for 25 AI coding agents: Claude Code, Codex, Cursor, Gemini CLI & more. Monitor, approve, and jump back from

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio

Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and

A CLAUDE.md built on Karpathy's principles and gstack, adding a verification harness and autonomous-loop rules for Claude Code.

🐙 盯着 Claude Code 的桌面宠物：随 agent 状态变表情、弹消息气泡、一键授权，并统计 token 用量与花费。本地优先、MIT。

One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and c

Deconstructing Claude Code — interactive source code analysis, guided wc/helpe walkthroughs, and deep architectural exploration of Anthropic