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
Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx cont
0,8/gün ort. +5 son gün — commit Python 02 Tem 2026 güncellendi 23 gün önce - 2
Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compr
1/gün ort. +2 son gün — commit Rust 23 Mar 2026 güncellendi 3 gün önce - 3
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via
9,2/gün ort. +1 son gün — commit Go 06 Nis 2026 güncellendi bugün - 4
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 — commit Python 27 Tem 2026 güncellendi 3 gün önce - 5
🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers
1,8/gün ort. +1 son gün — commit TypeScript 20 Haz 2026 güncellendi 29 Eyl 2026 - 6
Auto AI improver. Token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read hints, P
0,9/gün ort. +1 son gün — commit TypeScript 16 May 2026 güncellendi bugün - 7
A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre a
0,6/gün ort. +1 son gün — commit Rust 04 Nis 2026 güncellendi dün - 8
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
0,4/gün ort. +1 son gün — commit Go 10 Haz 2026 güncellendi 31 Ağu 2026 - 9
CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the con
0,2/gün ort. +1 son gün — commit Go 06 Mar 2026 güncellendi 5 gün önce - 10
Persistent memory system for Coding Agents (Claude, Opencode, Codex), infinite context, learning extraction, persona modeling and so much m
0,2/gün ort. +1 son gün — commit Go 09 Nis 2026 güncellendi 5 gün önce - 11
MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup
0,3/gün ort. +1 son gün — commit Rust 15 May 2026 güncellendi 02 Haz 2026 - 12
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt
2/gün ort. +0 son gün — commit Python 07 Mar 2026 güncellendi dün - 13
Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthrop
1,3/gün ort. +0 son gün — commit TypeScript 06 Tem 2026 güncellendi 8 gün önce - 14
Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
0,7/gün ort. +0 son gün — commit Python 01 May 2026 güncellendi 06 Eyl 2026 - 15
Safety-first GUI and CLI for auditing, backing up, importing, cleaning, and trimming Codex conversations without editing internal storage.
1,1/gün ort. +0 son gün — commit Python 12 Ağu 2026 güncellendi 02 Eyl 2026 - 16
Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix commands. Zero API calls
0,4/gün ort. +0 son gün — commit TypeScript 01 Nis 2026 güncellendi 9 gün önce - 17
A SillyTavern extension providing a multi-tier memory and narrative context system for AI roleplay. Tracks character facts, relationship his
0,3/gün ort. +0 son gün — commit JavaScript 03 Nis 2026 güncellendi 02 Eki 2026 - 18
Know your headroom. Context window usage bar for Claude Code.
0,4/gün ort. +0 son gün — commit Shell 23 Nis 2026 güncellendi 24 Nis 2026 - 19
Session handoffs for Claude Code: skills that capture decisions, failed approaches and next steps, plus a Claude Code mod (/compact-handoff)
0,3/gün ort. +0 son gün — commit TypeScript 20 Mar 2026 güncellendi 6 gün önce - 20
Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows w
0,2/gün ort. +0 son gün — commit TypeScript 21 Mar 2026 güncellendi 16 Nis 2026 - 21
What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each
0,5/gün ort. +0 son gün — commit TypeScript 07 Ağu 2026 güncellendi dün - 22
Real-time statusline, live monitor, session analytics, and hooks for Claude Code
0,2/gün ort. +0 son gün — commit Python 08 Mar 2026 güncellendi 4 gün önce - 23
Losslessly compress the tool output your AI agent sends the model, prove every value survived, and report the exact tokens removed. Run it a
0,4/gün ort. +0 son gün — commit Rust 20 Tem 2026 güncellendi 11 gün önce - 24
Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.
0,2/gün ort. +0 son gün — commit Python 17 Nis 2026 güncellendi 25 Nis 2026