Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 1
Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code
2/gün ort. +9 son gün 129 commit 1 yazar JavaScript 31 Ağu 2026 güncellendi 2 gün önce - 2
Compartment is a self-hosted deployment system for small software on infrastructure your team controls.
1,3/gün ort. +0 son gün 0 commit 0 yazar TypeScript 25 May 2026 güncellendi 20 Ağu 2026 - 3
An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the com
1,1/gün ort. +31 son gün — commit Rust 16 Haz 2026 güncellendi bugün - 4
Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.
0,8/gün ort. +0 son gün — commit Python 26 Eyl 2026 güncellendi 29 Eyl 2026 - 5
Agents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a t
0,5/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi dün - 6
Laravel audit log & change history with real actor attribution (user / job / command / scheduler), cross-model change traces, time machine,
0,5/gün ort. +0 son gün — commit PHP 10 Haz 2026 güncellendi 30 Haz 2026 - 7
Run SQL on production databases with approval and a full audit. Users submit from Slack or a web IDE, and a DBA approves. QueryHub runs the
0,3/gün ort. +0 son gün — commit Python 31 Tem 2026 güncellendi bugün - 8
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
0,3/gün ort. +0 son gün — commit HTML 12 Ağu 2026 güncellendi 28 Ağu 2026 - 9
AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts any
0,2/gün ort. +0 son gün — commit Rust 13 Ağu 2026 güncellendi 04 Eyl 2026 - 10
Open-source security for AI coding agents: record, detect and block at the tool boundary, with a verifiable audit trail in the SIEM you alre
0,2/gün ort. +0 son gün — commit Python 02 Tem 2026 güncellendi bugün - 11
Self-hosted counter-surveillance for the networks you control: map device and network exposure, verify trusted routes, and hold sensitive ac
0,2/gün ort. +0 son gün — commit Go 22 Tem 2026 güncellendi 2 gün önce - 12
A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule o
0,1/gün ort. +0 son gün — commit Python 01 Haz 2026 güncellendi 11 Haz 2026 - 13
TypeScript SDK for the NitroPing audit log — batching client, error capture, Hono/Express/Nitro adapters, and GenAI cost tracing.
0,1/gün ort. +0 son gün — commit TypeScript 22 May 2026 güncellendi 26 Ağu 2026 - 14
Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-chec
0,1/gün ort. +0 son gün — commit Rust 02 Ağu 2026 güncellendi bugün - 15
MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-
0,1/gün ort. +0 son gün — commit TypeScript 18 Tem 2026 güncellendi 2 gün önce