Multi-tenant fine-tuning for LLMs with Tinker-compatible API
-
Updated
Sep 2, 2026 - Python
#
local-llms
Here are 54 public repositories matching this topic...
Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.
macos swift metal moe gemma macos-app mixture-of-experts on-device-ai apple-silicon large-language-models llm local-inference local-llm llm-inference local-ai qwen local-llms openai-compatible gpt-oss model-offloading
-
Updated
Sep 11, 2026 - Swift
CROW - Your AI Agent. MCPs, OpenRouter, Any Model or local. It's your choice.
windows mcp cuda inference persistent-memory tool-use local-first coding-assistant ai-agent llm long-context anthropic llama-cpp openrouter qwen gguf agentic-ai local-llms qwen3 coding-agent
-
Updated
Sep 19, 2026 - Python
Notolog Markdown Editor
markdown text-to-speech qt markdown-editor python3 onnx on-device-ai ai-assistant pyside6 python-qt local-inference llama-cpp local-llm qwen llama-cpp-python gguf local-llms phi-4 privacy-first-ai nemo-speech
-
Updated
Sep 7, 2026 - Python
Fast-ASDLC: 5x TTM with AI-native Agentic SDLC. Local-LLM first, Human-in-the-loop, Spec-driven. Built on DDD, Hexagonal Architecture, C4 Model & MCP. Features Meta-agents for self-improvement, Memory Bank for context persistence, and automated 100% test coverage. Everything-as-Code & Mermaid.js centric to save context window and slash token costs.
ddd software-engineering hexagonal-architecture solid-principles everything-as-code c4-model devops-automation ai-native local-llm llm-agents local-llms mcp-servers spec-driven-development agentic-sdlc asdlc llm-agents-coding-agents fast-asdlc
-
Updated
Jul 1, 2026
Describe images with Ollama
accessibility a11y command-line-utility describe-image llm large-language-model llava ollama ollama-client llm-manager local-llms
-
Updated
Jun 5, 2026 - Go
A from-scratch implementation of the language-model training pipeline in PyTorch: tokenization, pretraining, SFT, and preference-based alignment.
nlp machine-learning deep-learning pytorch transformer alignment educational from-scratch sft dpo llm generative-ai rlhf local-llms grpo
-
Updated
Jul 14, 2026 - Python
🚀 Unified NLP Pipelines for Language Models
tokenizer embeddings chunking semantic-search knowledge-distillation bert reranking pinecone faiss roberta huggingface data-labeling large-language-models masked-language-modeling llms chromadb ollama local-llms
-
Updated
Feb 27, 2026 - Python
Delta: LLM conversation branching
-
Updated
Dec 30, 2024 - TypeScript
J.A.R.V.I.S: An AI-powered Open Source Intelligence (OSINT) system. It orchestrates deep web scraping and local LLMs to autonomously generate comprehensive intelligence dossiers.
react python agent intelligence automation typescript osint ai nextjs postgresql web-scraping beautifulsoup jarvis fastapi ai-assistant local-llm ollama local-llms
-
Updated
Sep 13, 2026 - Python
Playground for learning by doing
python learning programming learning-python coding developer-tools text-summarization software-engineering software-development experiments learning-by-doing research-and-development coding-practices cli-tools ai-tools local-llms
-
Updated
Mar 27, 2026 - Jupyter Notebook
A Unity package for building open-source AI voice agents that run fully locally. You can use it to build intelligent non-player characters (NPCs), game interfaces, among many other applications.
gamedev unity gamedev-library gamedevelopment voice-ai voice-agent pipecat local-llm local-ai voice-agents local-llms pipecat-ai
-
Updated
Sep 17, 2026 - MDX
XR — the secure, self-hosted AI agent. BYOK · local-first · spend-capped · tamper-evident. by rrrtx
security typescript ai ai-agents bun xr ai-assistant ai-agent byok llms ollama local-llms byok-ai-tools-code-assistant
-
Updated
Sep 19, 2026 - TypeScript
Nova Studio - Windows desktop workbench for local LLM inference (vLLM / SGLang / llama.cpp via WSL2), bridging WSL engines to any OpenAI-compatible client
desktop-app windows api-gateway wsl llama-cpp vllm local-llm sglang local-llms local-llm-integration local-llm-gguf local-llm-agent local-llm-ollama
-
Updated
Aug 19, 2026 - TypeScript
The Operating System for Local Intelligence. ⚙️
rust kernel firewall rust-lang multi-agent-systems orchestrator ai-agents local-llms gpu-multiplexing wasm-sandbox cross-language-agents-tooling cross-language-memory-fusion
-
Updated
Sep 11, 2026 - Rust
🤖 Autonomous AI career engine — scans 28,700+ real tech company ATS boards (Greenhouse, Lever, Ashby, Workday & SmartRecruiters), monitors Wellfound alerts + custom career pages, scores via cosine similarity + LLM rubrics, generates STAR-tailored pitches for 1-click review. 100% Free.
reactjs web-scraper python3 careers sqlite3 autonomous-agents ai-agents automations gemini-api windows-11 job-search-engine fast-api local-first freeware-lovers llms resume-analyzer local-llms ats-scanner ollama-local-llm playrwright
-
Updated
Aug 22, 2026 - HTML
A lightweight CLI to orchestrate Gemini and GPT using your local files as a shared blackboard.
cli ai multi-agent gemini openai gpt agents grok multi-agent-systems claude ai-tools chatgpt agentic-workflow local-llms multi-agents-collaboration
-
Updated
Mar 24, 2026 - Python
A minimalist terminal script that analyzes your hardware and use cases to recommend the best local AI models you can reliably run. Powered by the free Gemini 3.1 Flash Lite model, it uses your own Google API key at runtime. You can generate your key for free in under 90 seconds in Google AI Studio, and that's completely safe & costs nothing!
-
Updated
Jul 6, 2026 - Python
Local-first RAG endpoint that answers cheap questions locally and escalates hard ones to the cloud automatically, behind your LLM Proxy
-
Updated
Aug 4, 2026 - Python
GGUF-Runner - Want to run LLMs locally, use this guide, and run with LLAMA.cpp
-
Updated
May 4, 2026
Add this topic to your repo
To associate your repository with the local-llms topic, visit your repo's landing page and select "manage topics."