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
One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 ->
4,2/gün ort. +1 son gün 151 commit 3 yazar Python 27 Tem 2026 güncellendi 3 gün önce - 2
The one place for the skills, keys and memory of every agent you use. Formerly OMNI.
1,6/gün ort. +2 son gün 121 commit 2 yazar Rust 15 Mar 2026 güncellendi 2 gün önce - 3
An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio
0,8/gün ort. +1 son gün — commit Go 01 May 2026 güncellendi dün - 4
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
0,6/gün ort. +1 son gün — commit Go 15 Nis 2026 güncellendi 03 Ağu 2026 - 5
Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code
2/gün ort. +9 son gün 129 commit 1 yazar JavaScript 31 Ağu 2026 güncellendi 2 gün önce - 6
HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code
0,9/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 7
Token Cost Parity: Multilingual LLM Efficiency Analysis 2026
0,9/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 8
dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive
3,7/gün ort. +0 son gün 15 commit 1 yazar TypeScript 04 Eki 2026 güncellendi 2 gün önce - 9
Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own
1,2/gün ort. +0 son gün 8 commit 1 yazar JavaScript 19 Ağu 2026 güncellendi 11 gün önce - 10
The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless roun
0,4/gün ort. +0 son gün — commit 03 Haz 2026 güncellendi bugün - 11
Claude Code skills for developers who code like cats — never more effort than the problem requires.
0,3/gün ort. +0 son gün — commit JavaScript 04 Haz 2026 güncellendi 02 Eki 2026 - 12
Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.
0,2/gün ort. +0 son gün — commit Python 09 Nis 2026 güncellendi 15 Nis 2026 - 13
Local OpenAI/Anthropic-compatible proxy using structured conversation state to reduce repeated context. Savings and compatibility depend on
0,5/gün ort. +0 son gün — commit TypeScript 30 Ağu 2026 güncellendi 10 gün önce - 14
Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents
0,3/gün ort. +0 son gün — commit HTML 10 Tem 2026 güncellendi 21 gün önce - 15
Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email.
0,2/gün ort. +0 son gün — commit Python 28 Haz 2026 güncellendi bugün - 16
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory via SQLite + FTS5, and enfo
1,4/gün ort. -5 son gün — commit JavaScript 17 Eki 2026 güncellendi 17 gün önce - 17
Drop-in instructions, prompts, and workflows to reduce token usage across Codex, Claude Code, GitHub Copilot, Cursor, and other AI coding ag
0,1/gün ort. +0 son gün — commit Python 17 Haz 2026 güncellendi dün - 18
Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max wit
0,5/gün ort. +0 son gün — commit Python 27 Eyl 2026 güncellendi 30 Eyl 2026 - 19
A governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory
0,1/gün ort. +0 son gün — commit JavaScript 01 May 2026 güncellendi 6 gün önce - 20
A smart, multi-strategy code compressor
0,1/gün ort. +0 son gün — commit JavaScript 16 Haz 2026 güncellendi 18 Haz 2026 - 21
Persistent coding intelligence for Codex — project-aware context, adaptive reasoning, scoped changes, and risk-aware verification.
0,1/gün ort. +0 son gün — commit Python 07 Ağu 2026 güncellendi 05 Eyl 2026 - 22
扫出并清除「自称已废」的墓碑 skill、AI 幽灵碎片与死代码，统计释放的 Token 与磁盘。· An agent skill that reaps tombstoned skills, agent leftovers and dead code, reporting tok
0/gün ort. +0 son gün — commit Shell 18 Eyl 2026 güncellendi bugün