KirishAkkaunt yaratish
KirishAkkaunt yaratish

awesome-llm-apps

Ochiq manbalardan

awesome-llm-apps — Apache-2.0 litsenziyasi ostidagi bepul ochiq kod toʻplami: 100 dan ortiq AI agentlar, agent koʻnikmalari va RAG ilovalari.

AI vositaKategoriya: AI vositalariOpen sourcemaʼlumot tekshirilgan: 15-okt, 2026
SolishtirishToʻplamga

Sharh

Noldan ishlaydigan LLM ilovasini yaratish koʻp vaqt talab qiladi, ko‘pchilik ochiq misollar esa asl muhitidan tashqarida ishlamaydi. awesome-llm-apps — 100 dan ortiq AI agentlar, agent koʻnikmalari va RAG ilovalaridan iborat ochiq kod toʻplami. Har bir loyiha qoʻlda yozilgan va boshidan oxirigacha sinovdan oʻtkazilgan, shuning uchun dasturchi boʻsh fayldan emas, tayyor ishchi loyihadan boshlashi mumkin. Katalogda bitta API kaliti bilan ishlaydigan boshlangʻich agentlar, vositalar va xotiraga ega murakkab koʻp agentli ilovalar, jadval boʻyicha ishlaydigan fon agentlari hamda bitta buyruq bilan oʻrnatiladigan koʻnikmalar mavjud. Loyihalar Claude, Gemini, GPT, DeepSeek, Llama, Qwen va boshqa ochiq modellar bilan ishlaydi. Repozitoriy Apache-2.0 litsenziyasi ostida tarqatiladi. Har qanday shablonni klonlash, pip install va Streamlit buyrugʻi orqali mahalliy ishga tushirish hamda oʻz ehtiyojlaringizga moslashtirish mumkin.
  • agent-skills
  • agents
  • llms
  • python
  • rag

Oʻrnatish

Buyruqlar faqat koʻrsatiladi, marketpleys ularni bajarmaydi. Rasmiy hujjatlar bilan solishtiring.

Moslik

«Nomaʼlum» dalil topilmaganini bildiradi, mahsulot mos emasligini emas.
PlatformaHolatArxitekturaDalilIshonchlilik
WindowsNomaʼlum———
macOSNomaʼlum———
LinuxNomaʼlum———
Web browserNomaʼlum———
Server / self-hostedNomaʼlum———
Container (OCI)Nomaʼlum———

Relizlar

tekshirilgan: 29-okt, 2026
Manbada relizlar topilmadi.

Sifat profili

algoritm quality-v1.0 · baholangan 15-okt, 2026
Sifat bahosi86
Xavf bahosi0
Ishonchlilik 1.00
Sifat bahosi va xavf bahosi — turli koʻrsatkichlar. Yuqori sifat xavfsizlikni kafolatlamaydi.

Baho tarkibi

Qoʻllab-quvvatlash · 2020
last activity 0 days ago
Hujjatlar · 1515
README 25669 chars, description present
Foydalanishga tayyorlik · 159
install instructions: yes; releases: no
Metamaʼlumotlar · 1010
4/4 of description, homepage, license, topics
Relizlar · 102
0 release(s)
Kategoriya aniqligi · 1010
classifier confidence 1
Ommaboplik · 1010
141881 stars (log-dampened, 10k = max)
Litsenziya aniqligi · 55
SPDX Apache-2.0
Hamjamiyat · 55
issues enabled, 20858 forks

Litsenziya

Apache-2.0
Litsenziya maʼlumrepozitoriy xostingi maʼlumotlariga koʻra

Bu katalog siyosati holati, yuridik xulosa emas.

Manbalar

github.com/Shubhamsaboo/awesome-llm-appsAsosiy★ 141 881 yulduzfaollik: 15-okt, 2026Asosiy repozitoriy · Ishonchlilik 1.00

Sharhlar

Sharh yozish uchun kiring

Hali sharhlar yoʻq.

Muqobillar

agenticaOʻxshash
Bir inson, agentlar jamoasi. Bir nechta terminalda birgalikda ishlaydigan koʻp seansli CLI; /goal uzoq vazifalarni davom ettiradi; WeChat/WeCom/Feishu shlyuzi esa siz uzoqlashganingizda ular bilan qayta bogʻlanish imkonini beradi. Asinxron Python SDK, doimiy xotira, oʻz-oʻzini takomillashtiruvchi koʻnikmalar.Apache-2.0 · AI vositalari
Hyper-ExtractOʻxshash
Hypergraph — kuchliroq vosita. LLM yordamida tuzilmasiz matnni tuzilmali bilimga aylantiring. Graflar, gipergraflar va fazoviy-vaqtiy ajratib olishlar — bitta buyruq bilan.AI vositalari
awesome-copilotOʻxshash
Awesome Copilot — hamjamiyat tomonidan yigʻilgan ochiq manbali toʻplam: GitHub Copilot uchun maxsus agentlar, koʻrsatmalar, koʻnikmalar va plaginlar.MIT · AI vositalari
ollamaOʻxshash
Ollama — Gemma, DeepSeek, Qwen va gpt-oss kabi ochiq modellarni mahalliy yoki bulutda ishga tushirish uchun ochiq manbali AI vosita; CLI, REST API va Python hamda JavaScript kutubxonalari bilan.MIT · AI vositalari
ragflowOʻxshash
RAGFlow — agent imkoniyatlariga ega ochiq kodli RAG dvigateli boʻlib, tuzilmagan hujjatlarni LLM ilovalari uchun asoslangan kontekst qatlamiga aylantiradi.Apache-2.0 · AI vositalari
open-webuiOʻxshash
Open WebUI — oʻz serverингizda joylashtiriladigan, kengaytirilishi mumkin boʻlgan sun’iy intellekt veb-interfeysi boʻlib, Ollama va istalgan OpenAI-mos API’larni mahalliy hamda bulutli modellar uchun bir joyga birlashtiradi.AI vositalari

README

Shubhamsaboo/awesome-llm-apps dan · litsenziya Apache-2.0 · yuklangan 29-okt, 2026

Awesome LLM Apps

100+ open-source AI agents, agent skills, and RAG apps. Hand-built, tested end-to-end, Apache-2.0.

Clone it, ship it, sell it - 100% free and open-source

Works with Claude, Gemini, GPT, DeepSeek, Llama, Qwen and other open-source models.

Step-by-step tutorials on Unwind AI · Quick start · Browse all templates

🚀 Run one now

Give your coding agent a new skill in 10 seconds:

npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyard

Then ask it: "why do I never finish my side projects?"

Or clone and run any agent in 30 seconds:

git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/ai_travel_agent
pip install -r requirements.txt
streamlit run travel_agent.py

📬 New templates drop weekly. Get them in your inbox on Unwind AI.

📂 Browse all templates

🧩 Agent Skills

Give your coding agent new abilities. One command to install, plain English to use. Every skill ships real code and passes a security + eval CI gate. Works with Claude Code, Codex, Cursor, and other coding agents. Browse all skills →

  • ⚰️ Project Graveyard - Finds every side project you abandoned, tells you why each one died, and helps you finish the one worth going back to
  • 👁️ First Reader - Simulates real readers going through your draft and reports where they lose interest, where they stop reading, and what they remember afterward, without rewriting a word
  • 🔭 Scope Creep Detector - Checks whether a diff grew beyond its stated intent and recommends what to keep, split, or justify
  • 🏺 Commit Archaeologist - Reconstructs why a file or code region exists from its introducing commit, later edits, co-changes, and intent clues
  • 🩺 Dependency Doctor - Checks a dependency manifest for standard-library pins, obsolete backports, unpinned entries, duplicate constraints, and yanked releases
  • 🧠 Advisor Orchestrator Worker - Meta Loop with Claude Fable 5.1 as advisor, GPT-6 Astra as orchestrator, and Gemini 3.8 Flash as worker
  • 🎙️ Thinking Out Loud - Echoes a voice ramble back as a scannable brief, with the model's guesses quarantined and your reversals flagged
  • ♾️ Self-Improving Agent Skills - Automatically optimize agent skills using Gemini and ADK

🛠️ Standalone Apps & Tools

Standalone web apps, creative tools, and browser extensions for everyday workflows.

🌱 Starter AI Agents

Single-file agents that run with just an API key - a great place to start.

🚀 Advanced AI Agents

Production-style agents with tools, memory, and multi-step reasoning.

🛰️ Always-on Agents

Background agents that run on schedules or events, monitor changing context, decide what needs attention, and proactively deliver updates, artifacts, or actions.

🤝 Multi-agent Teams

Multiple agents collaborating to accomplish complex, cross-domain tasks.

🗣️ Voice AI Agents

Speech-in, speech-out agents using real-time voice APIs.

🖼️ Generative UI and Agentic Frontends

Agents that render interactive UI components, not just text: forms, cards, charts, editable plans.

🎮 Autonomous Game-Playing Agents

Agents that play games end-to-end: reasoning, strategy, and action.

♾️ MCP AI Agents

Agents that connect to external tools and data via Model Context Protocol.

📀 RAG (Retrieval Augmented Generation)

Retrieval pipelines, from simple chains to agentic and multi-source.

💾 LLM Apps with Memory

Agents and chatbots that remember conversations and user state across sessions.

💬 Chat with X

Turn any data source into a chat interface.

🎯 LLM Optimization Tools

Reduce token usage, context size, and API cost without losing quality.

🔧 LLM Fine-tuning

End-to-end fine-tuning recipes for open-source models.

🧑‍🏫 AI Agent Framework Crash Courses

Deep-dive tutorials on the major agent frameworks.

  • Google ADK Crash Course - Starter agent, structured outputs, tools (built-in, function, third-party, MCP), memory, callbacks, plugins, and multi-agent patterns. Model-agnostic.
  • OpenAI Agents SDK Crash Course - Starter agent, function calling, structured outputs, tools, memory, evaluation, handoffs, swarm orchestration, and routing logic.

⭐ Star the repo to get notified when new templates drop.

Apache-2.0 · See LICENSE · Fork it, ship it, sell it.

Repozitoriyni ochish ↗