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
AgentGuard: Zero-Trust Security Foundation for AI Agents
1/gün ort. +2 son gün +0,6 son 7g — commit Python 27 May 2026 güncellendi 3 gün önce - 2
Harness-oriented agent system framework for production-grade LLM agent applications
3,6/gün ort. +0 son gün +0,3 son 7g 0 commit 0 yazar TypeScript 01 Tem 2026 güncellendi 04 Eyl 2026 - 3
Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, ca
0,6/gün ort. +2 son gün +0,3 son 7g — commit Rust 22 Mar 2026 güncellendi 4 gün önce - 4
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and
0,2/gün ort. +1 son gün +0,3 son 7g — commit Go 24 Mar 2026 güncellendi 7 gün önce - 5
Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalat
0,2/gün ort. +0 son gün +0,3 son 7g — commit TypeScript 04 Ağu 2026 güncellendi bugün - 6
Policy-governed execution layer for AI systems. Enforces deterministic decisions and produces verifiable audit evidence.
0,1/gün ort. +0 son gün +0,3 son 7g — commit Python 24 Haz 2026 güncellendi bugün - 7
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
2,4/gün ort. +0 son gün +0,1 son 7g 0 commit 0 yazar TypeScript 19 Mar 2026 güncellendi 08 Tem 2026 - 8
Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in.
0,9/gün ort. +1 son gün +0,1 son 7g — commit Rust 01 Nis 2026 güncellendi 22 Haz 2026 - 9
CloakPipe is the verifiable control plane for production AI agents: evaluate a release, certify it, enforce it at runtime, and prove what ha
0,2/gün ort. +1 son gün +0,1 son 7g — commit Rust 06 Mar 2026 güncellendi 5 gün önce - 10
AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL
0,2/gün ort. +0 son gün +0,1 son 7g — commit Go 08 May 2026 güncellendi 02 Eyl 2026 - 11
The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a
0,3/gün ort. +1 son gün +0,1 son 7g — commit Python 24 Tem 2026 güncellendi 4 gün önce - 12
Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.
1,9/gün ort. +0 son gün +0 son 7g 0 commit 0 yazar Go 18 Ağu 2026 güncellendi 25 Ağu 2026 - 13
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 son 7g 0 commit 0 yazar Python 20 Tem 2026 güncellendi 22 Tem 2026 - 14
Agent wallet infrastructure — encrypted keys, policy enforcement, credential proxy, auth platform. Self-hostable, multi-tenant, open source.
0,4/gün ort. +0 son gün +0 son 7g — commit TypeScript 13 Mar 2026 güncellendi dün - 15
Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.
1,2/gün ort. +0 son gün +0 son 7g — commit Python 18 Ağu 2026 güncellendi 19 Ağu 2026 - 16
Real-time guardrail runtime for AI agents.
0,1/gün ort. +0 son gün +0 son 7g — commit Rust 10 May 2026 güncellendi 8 gün önce - 17
Approval workflow components for React Flow, distributed as a shadcn registry. Quorum gates, thresholds, policy lint, plain-language editing
0,2/gün ort. +0 son gün +0 son 7g — commit TypeScript 08 Tem 2026 güncellendi 14 Eyl 2026 - 18
Offline personal-agent runtime + life apps: seeded persona factory with planted ground truth, tool registry, policy engine with PII redactio
5,3/gün ort. +0 son gün +0 son 2g 22 commit 1 yazar Python 30 Eki 2026 güncellendi 4 gün önce - 19
Policy-aware field mission orchestration agent with bounded planning, auditable replanning, travel and expense constraints.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 09 Tem 2026 güncellendi 11 Ağu 2026 - 20
Annona — the sovereign execution kernel for AI agents. Decides where each step runs, enforces it, and records it.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 30 Tem 2026 güncellendi dün - 21
SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy con
0,1/gün ort. +0 son gün +0 son 7g — commit Python 10 Haz 2026 güncellendi 10 gün önce - 22
Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew
0,4/gün ort. +0 son gün +0 son 7g — commit Go 24 Eyl 2026 güncellendi dün - 23
Deterministic safety solutions for probabilistic AI agents
2,1/gün ort. +0 son gün -0,1 son 7g 22 commit 2 yazar Python 04 Nis 2026 güncellendi 4 gün önce