QLoRA: Efficient Finetuning of Quantized LLMs
Repository Index
60,121 visible repositories in the index
25–48 of 61 · Most stars
Locally run an Instruction-Tuned Chat-Style LLM
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
- gateway
- llm-gateway
- guardrails
- mcp-gateway
Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro, OpenAI, Claude, and custom providers. Supports OpenAI-compatible API, Claude API, Gemini protocol conversion, GPT, Grok Build, Claude Opus, Gemini Pro, Kimi, MiniMax, provider pools, smart routing, and automatic failover.
- aicoding
- free
- antigravity
- codex
World's first open-source enterprise world model.
- agent-memory
- knowledge-base
- knowledge-graph
- llm
Accessible large language models via k-bit quantization for PyTorch.
- llm
- machine-learning
- pytorch
- qlora
An open, programmable decision layer for models and compute.
- mixture-of-models
- semantic-router
- vllm
- ai-gateway
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
- embeddinggemma
- embeddings
- llama-cpp
- local-first
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.
- document-parser
- embeddings
- llm
- open-source
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
- ai
- ast
- claude-code
- code-analysis
TranslatedConverts Antigravity into OpenAI, GEMINI, and Claude API interfaces
- gemini
- gemini-ai
- gemini-api
- gemini-pro
Repair malformed JSON from LLMs, APIs, logs, and user input in Python.
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
CISO Assistant is a one-stop-shop GRC platform for Risk Management, AppSec, Compliance & Audit, TPRM, BIA, Privacy, and Reporting. It supports 200+ global frameworks with automatic control mapping, including ISO 27001, NIST CSF, SOC 2, CIS, PCI DSS, NIS2, DORA, GDPR, HIPAA, CMMC, and more.
- compliance
- grc
- soc2
- gdpr
Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.
- chromadb
- dashcam
- gemini
- gemini-embedding-2
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
- agent-memory
- agentic-ai
- ai-reasoning
- episodic-memory
Proxy that exposes Antigravity provided claude / gemini models, so we can use them in Claude Code and OpenClaw (Clawdbot)
- antigravity
- claude
- claude-code
- gemini
Open-source web scraping API. Turn any website into clean markdown or structured JSON. Anti-detect browser, proxy auto-selection, self-hosted. One command: make up
Local-first desktop widget for tracking token usage, costs, limits, and session activity across 54+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.
Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.
- developer-tools
- golang
- quota-tracker
- ai-api-monitoring