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
Ekbasis: an open world model for agents. What an action will do, before it is done.
0,6/gün ort. +0 son gün — commit Python 04 Eki 2026 güncellendi 20 gün önce - 2
Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell
0,9/gün ort. +1 son gün — commit TypeScript 16 Eyl 2026 güncellendi 6 gün önce - 3
Zero-dependency guardrail framework for AI agents. Stops runaway loops, prompt injection, hallucination and unsafe tool calls before they ex
0,2/gün ort. +0 son gün — commit TypeScript 29 Ağu 2026 güncellendi bugün - 4
白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。
7,2/gün ort. +7 son gün 1.304 commit 8 yazar Python 14 Ağu 2026 güncellendi bugün - 5
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 - 6
Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become perman
0,2/gün ort. +0 son gün — commit Go 26 Tem 2026 güncellendi 27 gün önce - 7
Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable
1,3/gün ort. +0 son gün 0 commit 0 yazar Python 20 Tem 2026 güncellendi 22 Tem 2026 - 8
Undo for AI agent shell commands. Snapshots files before Claude Code runs destructive bash (rm -rf, git reset, rsync), so agent mistakes are
0,3/gün ort. -1 son gün — commit Rust 06 Tem 2026 güncellendi 19 Ağu 2026 - 9
The agent's prompt shows you the command; Termaxa shows you the consequence. Previews, backups, policy, an audit record. Claude Code, Codex,
0,2/gün ort. +0 son gün — commit Rust 04 Tem 2026 güncellendi 2 gün önce - 10
Open-source runtime for grounded, model-agnostic computer-use agents with verifiable action receipts.
0,3/gün ort. +1 son gün — commit Python 12 Haz 2026 güncellendi 14 gün önce - 11
Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip instal
0,1/gün ort. +0 son gün — commit Python 25 May 2026 güncellendi 15 Ağu 2026 - 12
OpenClaw-compatible MASL safety gate with public RAG packs for memory-aware AI agents
0,1/gün ort. +0 son gün — commit Python 07 May 2026 güncellendi 13 gün önce - 13
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref
0,2/gün ort. +0 son gün — commit Shell 30 Nis 2026 güncellendi 30 Nis 2026 - 140/gün ort. +0 son gün — commit Python 26 Nis 2026 güncellendi 08 Ağu 2026
- 15
The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.
1,2/gün ort. +2 son gün — commit TypeScript 10 Nis 2026 güncellendi dün - 16
Deterministic safety solutions for probabilistic AI agents
2,1/gün ort. +0 son gün 22 commit 2 yazar Python 04 Nis 2026 güncellendi 6 gün önce - 17
An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27
0,4/gün ort. +0 son gün — commit Go 06 Mar 2026 güncellendi 10 Haz 2026