Havuz

Waku, yerel SQLite memory, agent loop ve eval araçlarını bir araya getiren, Python tabanlı kişisel AI assistant uygulamasıdır.

Neden yükseliyor · 79 günlük bir repo için 1.849 yıldızın yanında son 28 günde 30 commit ve 7 farklı yazar bulunması görünür ilgi ve devam eden geliştirme gösteriyor. README'nin sade, okunabilir agent loop ve entegre memory/eval yaklaşımı da projeyi agent harness arayan geliştiricilere çekici kılıyor; bu metrikler benimsenme veya üretim başarısını tek başına kanıtlamıyor.

Thenwise: a local memory of your past Claude Code work, searchable by date and link.

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

High-performance Go proxy gateway for 9Router LLM routing — 32K RPS, 42MB RAM, CGO-free

Always-on durable pi agent on your server that you talk to in Telegram. Survives crashes and restarts, keeps history in SQLite. pi-durable T

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with

Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-host

Local-first AI trading journal. Import your broker CSV, get round-trip trades, KPIs and Claude-powered diary analysis. Runs on your own mach

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

Self-hosted coordination for AI workers: per-task graphs, device/model timelines, progress receipts, and source-aware usage. MIT.

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats

Smart Promise Tracker AI 2026 – Commit Memory Engine

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseSt

跨平台 AI 编程助手用量监控桌面应用 | Cross-platform AI coding usage monitor: track Claude / Codex quota, tokens & costs. Data stays local.

An illustrated multi-agent village strategy game. Set objectives; residents gather, build, upgrade and recruit. Battle, inspect decisions an

📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & friends

Free, open-source local business intelligence audits for marketers and agencies. Run on your machine with real public data, and agentic work

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills co

Lightweight, async multi-agent framework with native SQLite persistence and handoffs for WhatsApp, Telegram, Webhooks, and CLI. Production-h

Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.

Self-hosted GEO & AI SEO dashboard. Track how ChatGPT, Claude, Gemini, Perplexity, DeepSeek and more mention and cite your brand, compare sh

Turn isolated Claude sessions into a continuous working relationship

Persistent working memory and invariant steering MCP server for AI coding agents (Claude Code, Cursor, Windsurf). Captures architectural dec

CRM local con IA que se personaliza a tu negocio. 100% local, open-source, powered by Claude Code. | AI-powered local CRM that customizes it

Persistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. Hosted

Local-first Proton Mail MCP server and CLI via Proton Bridge. Search, draft, send and organize mail from Claude Desktop, Claude Code or any

我们的港湾

Persistent, interactive MCP Apps for any MCP host: the AI builds an app once, you both reuse it — data outlives the conversation. Ships an e

SkillRoute by JEStats — local-first skill routing for coding agents, with ranked matches, confidence, and evidence over MCP.

Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge gra

Free open-source business data enrichment engine. The open-source alternative to Apollo, ZoomInfo, and Clearbit.

A task board Claude fills in for itself: a Claude Code plugin that mirrors Claude's task list onto a per-project board, with MCP tools and a

Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation. Cloud Run service + MCP tools.

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-we

Long-term memory for Claude Code. Indexes every session as SQLite+FTS5, exposes recall via MCP, and ships PreCompact/PostCompact hooks so no

Track your daily prompt contributions across CLI coding agents

Real-time execution trace and cost intelligence for Claude Code

Persistent memory for Claude Code. Local SQLite + MCP + hooks.

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

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Mar

Connect any AI agent to your personal Telegram via the official Business API — no userbot, no ban risk, no Premium. Agent reads & searches f

A private-by-default, self-hosted focus system with projects, timers, daily insights, distraction nudges, and optional AI/MCP companions.

High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-on

Local-first second brain for your handwritten reMarkable notebooks, searched through Claude Desktop.

A local-first, LLM-agnostic memory layer for AI assistants

Apricity — a fast, local-first web UI for MemPalace: browse, search, edit & curate your AI agent's memory, knowledge graph & vector store. Z

Claude Code forgets everything between sessions. deja fixes that.

Local-first dashboard for tracking Codex, Claude Code, and GitHub Copilot token usage/spend by repo, session, model, and tool.

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief r