Shrink the web for your agents! Token-efficient, fast and fully local web search and research.
☆236Nov 12, 2026Updated this week
Alternatives and similar repositories for TinySearch
Users that are interested in TinySearch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A funny experiment with llama.cpp driving robots☆14Jul 27, 2026Updated 3 months ago
- RocketLLama. Fork off LLama cpp that newly scales 2-20x now also on big models not fully fitting in vram on even just 2 gpus☆16Updated this week
- Open WebUI tool: create Workspace Models (agent presets) from MODEL.md/JSON — native function calling, auto-bind knowledge/tools/skills. …☆12Aug 24, 2026Updated 2 months ago
- ☆40Aug 5, 2026Updated 3 months ago
- handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (arou…☆534Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A script to process ebooks into slideshows or movies through the use of several different types of generative AI.☆13Feb 20, 2026Updated 8 months ago
- Production-ready Open WebUI extensions, including Tools, Filters, Pipes, Actions, and Events for agent workflows, RAG, learning, automati…☆34Updated this week
- Qwen and DeepSeek low-VRAM LoRA training with GGUF base model, compatible with Transformers and PEFT☆22Nov 2, 2026Updated last week
- A text-grid web renderer for AI agents — see the web without screenshots☆103Mar 10, 2026Updated 8 months ago
- Lightweight Python tool using Optuna for tuning llama.cpp flags: towards optimal tok/s for your machine☆60Aug 17, 2026Updated 2 months ago
- ChatGPT-style generative UI for Open WebUI: photo galleries, live maps with real routes, multi-day trips, budgets, calculators, live weat…☆68Updated this week
- framework for using llms on object grounding☆25Oct 4, 2026Updated last month
- Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.☆33Aug 10, 2026Updated 3 months ago
- PLE n-gram knowledge injector for Qwen3.8-Flash-Next☆23Sep 3, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆42Jul 13, 2026Updated 3 months ago
- ☆11Nov 3, 2026Updated last week
- ☆18Dec 1, 2025Updated 11 months ago
- 3.34× faster inference on Apple Silicon: native MLX port of DFlash speculative decoding☆19Oct 7, 2026Updated last month
- Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecraw…☆1,244Updated this week
- A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by desi…☆546Oct 22, 2026Updated 3 weeks ago
- P2P semantic matching for on-device AI agents. No server, no cloud.☆20Jun 12, 2026Updated 5 months ago
- Fast, lightweight and stealth Firecrawl alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Fir…☆79Oct 18, 2026Updated 3 weeks ago
- A lightweight, prompt-driven MCP web research server for high-quality LLM powered information extraction.☆138Apr 10, 2026Updated 7 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Model for multi-turn tool calling of bash functions☆38Sep 7, 2026Updated 2 months ago
- ☆16Sep 25, 2026Updated last month
- ☆57May 29, 2026Updated 5 months ago
- ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, ver…☆61Sep 30, 2026Updated last month
- Multi-agent orchestration framework for AI applications - build, deploy, and manage AI agents across the full lifecycle with Forge, Conve…☆33Mar 28, 2026Updated 7 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,193Updated this week
- Qwen 3.8 Next Flash toolbox utilizing pwilkin's strix-halo llama.cpp fork☆13Sep 16, 2026Updated last month
- Local hybrid RAG over a code knowledge graph. Indexes your codebase with tree-sitter + embeddings + a relationship graph and serves preci…☆15May 29, 2026Updated 5 months ago
- An educational Rust project for exporting and running inference on Qwen3 LLM family☆44Aug 3, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.☆140Nov 2, 2026Updated last week
- a small python container that lets you proxy requests from claude's cloud container through your home network☆17Sep 26, 2026Updated last month
- LLM terms explained from an engineering perspective with the production implications, not just the definition.☆48May 23, 2026Updated 5 months ago
- Adding a multi-text multi-speaker script (diffe) that is based on a script from asiff00 on issue 61 for Sesame: A Conversational Speech G…☆26Mar 28, 2025Updated last year
- ☆11Jul 6, 2026Updated 4 months ago
- DocFinder is a local-first indexing and searching documents using semantic embeddings stored in SQLite. Everything runs on your machine, …☆36Updated this week
- Adds a /-/mcp MCP server to any Datasette instance☆20Oct 22, 2026Updated 3 weeks ago
Are these results useful?