Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

repo · sayfa 1 / 1

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

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

Sırala:

Etiketler yükleniyor…

Aktif safety

1
edaywalid/undo 402
Undo what the last shell command did to the filesystem
3,9/gün ort. +0 son gün 0 commit 0 yazar Go 23 Tem 2026 güncellendi 12 Ağu 2026
cli developer-tools filesystem ld-preload linux safety shell undo
402
2
aiming-lab/AutoHarness 465
AutoHarness: Automated Harness Engineering for AI Agents
2,2/gün ort. +1 son gün 0 commit 0 yazar Python 02 Nis 2026 güncellendi 02 Nis 2026
agent-framework ai-agents audit context-management governance harness-engineering llm multi-agent
465
3
PerryLink/dsh-permission-rules 136
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and
1,7/gün ort. +0 son gün — commit TypeScript 13 Ağu 2026 güncellendi 2 gün önce
ai-agent ai-agents ai-safety allow-deny-ask approval cordis deepseek deepseek-harness
136
4
agentscope-ai-java/redis-guard 20
Block FLUSHALL, KEYS and other dangerous Redis commands by policy, before they reach production.
0,5/gün ort. +0 son gün — commit Python 25 Eyl 2026 güncellendi 25 Eyl 2026
guard operations python redis safety zero-dependencies
20
5
ventianima-lab/codex-web-gpt-automation 53
Guarded, recoverable web ChatGPT automation for local Codex projects on Windows and macOS
0,5/gün ort. +0 son gün — commit Python 20 Tem 2026 güncellendi 09 Eyl 2026
ai-agents chatgpt chatgpt-automation codex developer-tools devspace macos mcp
53
6
datamllab/A2E 44
0,5/gün ort. +0 son gün — commit Python 06 Ağu 2026 güncellendi 23 gün önce
agent-audit agent-evaluation agent-observability agentic-ai ai-agents auditing llm-evaluation llm-tracing
44
7
hueyexe/opencode-auto-permissions 38
Automatic, model-driven permission review for OpenCode
0,4/gün ort. +0 son gün — commit TypeScript 04 Ağu 2026 güncellendi 17 Eyl 2026
ai-agents auto-approval automation cli developer-tools llm opencode opencode-plugin
38
8
justi/claude-code-project-boundary 90
Claude Code plugin: scope-aware protection — allows destructive ops (rm, mv, chmod) within project, blocks them outside. Built for dangerous
0,4/gün ort. +0 son gün — commit Shell 09 Mar 2026 güncellendi 02 Ağu 2026
claude-code claude-code-plugin dangerously-skip-permissions destructive-commands developer-tools safety cli-safety project-boundary
90
9
mokuyoaxis/agent-guard 26
Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliabili
0,4/gün ort. +0 son gün — commit Python 22 Ağu 2026 güncellendi 5 gün önce
ai-agents deepseek-harness dsh-plugin llm-tools safety
26
10
sadia-sigma-lab/BLINDSPOT 16
Live Benchmark for long Horizon tool using Agentic Systems
0,3/gün ort. +0 son gün — commit Python 14 Eyl 2026 güncellendi 16 Eyl 2026
agent-framework agentic-ai artificial-intelligence benchmark dataset large-language-models multi-agent over-refusal
16
11
OMD-123/agent-loop-guard 13
Protect AI agents from runaway loops, repeated tool calls, and uncontrolled execution. Provider-independent, zero-dependency, TypeScript-fir
0,2/gün ort. +0 son gün — commit TypeScript 29 Ağu 2026 güncellendi 24 gün önce
agent agent-safety ai ai-agent guard javascript llm loop-detection
13
12
dhilipmpms/SOS-alerter 34
Privacy-first SOS application for sending emergency messages and real-time location updates to trusted contacts.
0,2/gün ort. +0 son gün — commit Java 25 Nis 2026 güncellendi 26 Eyl 2026
android emergency-alert foss location-sharing open-source privacy privacy-focused security
34
13
AlekseiUL/agent-loop-engineering-kit 20
Design, validate, dry-run and audit safe Hermes Agent loop contracts before automation
0,2/gün ort. +0 son gün — commit Python 23 Haz 2026 güncellendi 5 gün önce
ai-agents automation hermes-agent loop-engineering safety
20
14
aryanbhosale/sh-guard 29
Semantic shell command safety classifier — AST-based risk scoring for AI coding agents
0,1/gün ort. +0 son gün — commit Rust 04 Nis 2026 güncellendi 13 Haz 2026
ai-agent bash claude-code cli codex command-injection cursor devtools
29
15
trvswgnr/prodkit 24
A runtime-agnostic, composable library for writing predictable operations in TypeScript.
0,1/gün ort. +0 son gün — commit TypeScript 21 Nis 2026 güncellendi 7 gün önce
error-handling operations safety typescript workflows
24
16
qarai-labs/qarai-agent-guard 16
A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt i
0,1/gün ort. +0 son gün — commit Python 23 May 2026 güncellendi 23 gün önce
agents arabic-nlp guardrails llm prompt-injection safety security
16
17
tonderaikawere/ktpasswordgenerator 15
A premium, highly-secure password generation utility. Designed to help users generate strong, cryptographically secure passwords and learn w
0,1/gün ort. +0 son gün — commit TypeScript 27 May 2026 güncellendi 19 Tem 2026
learning lessons password-generator react reactjs safety vite
15