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
Your agent’s trace says “success” but the answer is wrong. Tracedown finds the step that caused it and replays the run with a fix.
4/gün ort. +0 son gün 51 commit 7 yazar Python 30 Eki 2026 güncellendi bugün - 2
Cheaper and better Greptile alternative runs on your own github actions.
1,3/gün ort. -1 son gün 0 commit 0 yazar TypeScript 06 Ağu 2026 güncellendi 28 gün önce - 3
Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, re
0,7/gün ort. +0 son gün — commit Python 09 May 2026 güncellendi 3 gün önce - 4
Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com
0,6/gün ort. +0 son gün — commit TypeScript 20 May 2026 güncellendi 10 Tem 2026 - 5
半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.
0,4/gün ort. +0 son gün — commit TypeScript 08 May 2026 güncellendi 02 Haz 2026 - 6
End-to-end Langfuse workshop using a TypeScript Agent to teach the AI engineering loop: tracing, prompt management, monitoring, datasets, ex
0,4/gün ort. +0 son gün — commit TypeScript 19 May 2026 güncellendi 4 gün önce - 7
Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents
0,2/gün ort. +0 son gün — commit TypeScript 18 Mar 2026 güncellendi 11 Tem 2026 - 8
Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.
0,2/gün ort. +0 son gün — commit TypeScript 19 Mar 2026 güncellendi 06 Ağu 2026 - 9
Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token
0,4/gün ort. +0 son gün — commit TypeScript 21 Tem 2026 güncellendi 21 Tem 2026 - 10
Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-re
0,2/gün ort. +1 son gün — commit TypeScript 09 May 2026 güncellendi dün - 11
Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.
0,2/gün ort. +0 son gün — commit JavaScript 17 Haz 2026 güncellendi 2 gün önce - 12
Open-source control plane for private, governed enterprise AI — one gateway for every model, composable governed pipelines, and apps your wh
0,2/gün ort. +0 son gün — commit TypeScript 25 Haz 2026 güncellendi bugün - 13
Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p
0,2/gün ort. +0 son gün — commit TypeScript 22 Tem 2026 güncellendi 28 Eyl 2026 - 14
Deterministic cost / loop / time budgets · full observability · crash-resumable runs · human-approval gates · a memory you own. Self-hosted.
0,1/gün ort. +0 son gün — commit Go 30 May 2026 güncellendi 18 Eyl 2026 - 15
Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,
0,3/gün ort. +0 son gün — commit TypeScript 11 Eyl 2026 güncellendi 5 gün önce - 16
The whole eve stack. On your own machine. Durable Postgres sessions, a Docker sandbox, memory, approvals, schedules, 1,070 tool integrations
0,2/gün ort. +0 son gün — commit JavaScript 04 Ağu 2026 güncellendi 2 gün önce