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…
- 251
Agent Harness or sum
0,1/gün ort. — commit Rust 06 Tem 2026 güncellendi bugün - 252
Agent Doris CLI
0,1/gün ort. +0 son gün — commit Rust 29 May 2026 güncellendi 30 May 2026 - 253
CLI to organize temporary agent knowledge into scratchpads, with a read-only visual viewer.
0,1/gün ort. +0 son gün — commit TypeScript 07 Haz 2026 güncellendi 5 gün önce - 254
Build AI agents using the same architecture patterns as Claude Code. Skill + 6 examples + runnable Python code. No framework.
0,1/gün ort. +0 son gün — commit Mermaid 02 Nis 2026 güncellendi 03 Nis 2026 - 255
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
0,1/gün ort. +0 son gün — commit Python 10 Nis 2026 güncellendi 14 Nis 2026 - 256
DeSysFlow is a vibe designing tool just like vibe coding you can design your systems with clean docs
0,1/gün ort. +0 son gün — commit Python 06 Nis 2026 güncellendi 27 Nis 2026 - 257
embeddable llm agent in c with lua plugins
0,1/gün ort. +0 son gün — commit C 01 Tem 2026 güncellendi dün - 258
Lightweight agent that pulls and runs LLM benchmarks from Protorikis Bench
0,1/gün ort. +0 son gün — commit Python 10 Haz 2026 güncellendi 18 Haz 2026 - 259
A longitudinal reliability benchmark foundation for agent lifespan engineering.
0,1/gün ort. +0 son gün — commit Python 19 May 2026 güncellendi 05 Haz 2026 - 260
Review what your coding agents wrote. The agent walks you through each decision, and you comment back before you keep the change. Browser, M
0,1/gün ort. +0 son gün — commit TypeScript 13 Haz 2026 güncellendi bugün - 261
Codex-style /goal loops for Cursor Agent chat with local .goal state — no Agent SDK.
0,1/gün ort. +0 son gün — commit TypeScript 22 May 2026 güncellendi 26 May 2026 - 262
Local-first tool to visualize and analyze Claude Code, Cursor, Pi & OpenCode sessions — context tokens, LLM insights, governance artifacts.
0,1/gün ort. +0 son gün — commit TypeScript 18 Haz 2026 güncellendi 11 Ağu 2026 - 263
CLI coding agent powered by the MiMo large language model
0,1/gün ort. +0 son gün — commit TypeScript 29 May 2026 güncellendi 01 Haz 2026 - 264
Agentic AI monitoring and observability — OTEL traces and local log files from Copilot, Claude Code, Codex, and OpenCode. Token usage, cost,
0,1/gün ort. +0 son gün — commit TypeScript 24 May 2026 güncellendi dün - 265
Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.
0,1/gün ort. +0 son gün — commit Python 04 Haz 2026 güncellendi 05 Haz 2026 - 266
AgentInsight Python SDK provides a Python client for the AgentInsight platform, supporting LLM application observability, tracing, evaluatio
0,1/gün ort. +0 son gün — commit Python 02 Haz 2026 güncellendi 06 Tem 2026 - 267
Successor to ccg-workflow. Multi-model dev workflow for Claude Code — auto-routes frontend → Gemini, backend → Codex, with quality tiers,
0,1/gün ort. +0 son gün — commit TypeScript 06 May 2026 güncellendi 14 Haz 2026 - 2680,1/gün ort. +0 son gün — commit Rust 16 May 2026 güncellendi 27 gün önce
- 269
Stop reading AI replies. Your LLM places typed widgets (charts, kanbans, code, live timers) on an infinite canvas. Any model incl. local Oll
0,1/gün ort. +0 son gün — commit TypeScript 03 May 2026 güncellendi 3 gün önce - 270
Agent-first, zero-dependency, self-maintaining codebase documentation & change tracking system. LLM-operated wiki with health matrix, semant
0,1/gün ort. +0 son gün — commit Rust 15 May 2026 güncellendi dün - 271
Go LLM Execution Model — Go 原生 AI 编程 Agent CLI。单二进制、三层记忆、YAML 权限规则，TUI 对齐 Claude Code / Codex。
0/gün ort. +0 son gün — commit Go 04 Tem 2026 güncellendi 08 Tem 2026