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…
- 51
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 - 52
Redpen makes coding agents prove they are actually done.
0,4/gün ort. +0 son gün — commit TypeScript 12 Eyl 2026 güncellendi 05 Eki 2026 - 53
Hermes-native skill for systematic coding loops, real verification, and clean agent handoffs
0,1/gün ort. +0 son gün — commit Python 07 Tem 2026 güncellendi 10 Tem 2026 - 54
Chinese template for designing Multica multi-agent + skill workflows around task type, budget, models, and verification gates.
0,1/gün ort. +0 son gün — commit 05 May 2026 güncellendi 18 May 2026 - 55
Beginner-friendly Sol-led orchestration for Codex with pinned Luna and Terra workers and verified review.
0,2/gün ort. +0 son gün — commit Python 02 Ağu 2026 güncellendi 23 Eyl 2026 - 56
Gatemole compiles human-owned intent into obligations, links evidence artifacts to those obligations, and produces deterministic release dec
0,1/gün ort. +1 son gün — commit Go 06 May 2026 güncellendi 4 gün önce - 57
Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git state
0,1/gün ort. +0 son gün — commit Python 25 Haz 2026 güncellendi 3 gün önce - 58
Based on lectures on the LLM-Verifier Interface at the Summer School on Foundations of Programming and Software Systems (FoPSS 2026)
0,1/gün ort. +0 son gün — commit Python 01 Haz 2026 güncellendi 14 Tem 2026 - 59
Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.
0,1/gün ort. +0 son gün — commit Python 21 Haz 2026 güncellendi 03 Tem 2026 - 60
a DSL that blocks AI mistakes via proof
0,4/gün ort. +0 son gün — commit Clojure 21 Eyl 2026 güncellendi 10 gün önce - 61
For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI
0,1/gün ort. +0 son gün — commit TypeScript 18 May 2026 güncellendi 11 Eyl 2026 - 62
A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
0,1/gün ort. +0 son gün — commit 28 Haz 2026 güncellendi 07 Eyl 2026 - 63
A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve
0,1/gün ort. +0 son gün — commit Python 19 May 2026 güncellendi bugün - 64
A polygraph for your state machine: an LLM derives a formal model from your code, then Polygraph replays real traces against it and exhausti
0,1/gün ort. +0 son gün — commit JavaScript 07 Tem 2026 güncellendi 13 Eyl 2026 - 65
Interactive physics & CAE simulators. 1600+ educational tools with live demos at https://novasolver.jp
0,1/gün ort. +0 son gün — commit HTML 05 Haz 2026 güncellendi 30 Ağu 2026 - 66
"make", but for correctness claims. Decides when a coding agent's work is actually done, and un-decides it when you edit the code.
0,3/gün ort. +0 son gün — commit Python 09 Eyl 2026 güncellendi bugün - 67
A local verification receipt for AI coding agents
0,2/gün ort. +0 son gün — commit Go 12 Ağu 2026 güncellendi 30 Ağu 2026 - 68
The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/g
0,1/gün ort. +0 son gün — commit Python 31 Tem 2026 güncellendi 09 Eyl 2026 - 69
A small, file-first verification harness that turns an AI agent's "I'm done" claim into an auditable admission decision. 100% offline & zero
0,1/gün ort. +0 son gün — commit Go 21 May 2026 güncellendi 13 Ağu 2026 - 70
Evidence-driven multi-agent FPGA/SoC FPGA workflow for Codex: RTL, CDC/RDC, STA, verification, single-writer implementation, and independent
0,2/gün ort. +0 son gün — commit PowerShell 24 Ağu 2026 güncellendi 27 Ağu 2026 - 71
Task control for AI coding agents: explicit scope, bounded verification, durable state, safe recovery. Codex · Claude Code · DeepSeek · ZCod
0,2/gün ort. +0 son gün — commit Go 14 Ağu 2026 güncellendi bugün - 72
🛡️ An open-source trust verification CLI to validate and verify real-world claims with @openapi®.
0,1/gün ort. +0 son gün — commit Shell 17 Haz 2026 güncellendi 17 Haz 2026 - 73
Open-source local MCP runtime that checks AI-agent tool calls, gates risky actions on approval, verifies results, and avoids blind retries a
0,1/gün ort. +0 son gün — commit TypeScript 28 Tem 2026 güncellendi dün