AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.
☆2,027Aug 12, 2026Updated last month
Alternatives and similar repositories for smallcode
Users that are interested in smallcode 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 harness optimized to smaller LLMs☆2,658Sep 18, 2026Updated 3 weeks ago
- MarrowScript compiler. Welcome to deterministic typed LLM orchestration as a compile-time concern☆32May 21, 2026Updated 4 months ago
- Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents. Sub-millisecond queries, token budgeting, deterministi…☆24May 18, 2026Updated 4 months ago
- handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (arou…☆502Updated this week
- A declarative LLM friendly language that compiles system descriptions into complete, runnable Node.js backends.☆33Jun 24, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, br…☆1,593Updated this week
- ☆48Updated this week
- An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on yo…☆2,505Updated this week
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,906Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,288Updated this week
- Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser ch…☆247Jul 7, 2026Updated 3 months ago
- A minimal, local-first coding agent for the terminal.☆219Sep 25, 2026Updated 2 weeks ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,150Updated this week
- An AI-assisted coding agent that runs in your terminal and supports many providers and models.☆231Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,362Updated this week
- Open-source framework for superagents.☆114Sep 11, 2026Updated 3 weeks ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,904Updated this week
- Using LLMs for iteratively exploring the solution search space at scale.☆738Sep 5, 2026Updated last month
- A composable agent runtime — pair any frontend with any agent backend.☆67Updated this week
- TRELLIS.2 image-to-3D in C++/GGML (CUDA + Vulkan), with a resident HTTP server☆336Sep 25, 2026Updated 2 weeks ago
- Lightweight coding agent written in Rust, optimized for memory footprint and performance☆1,701Updated this week
- Personal Pi coding agent setup☆342Aug 16, 2026Updated last month
- Local-first AI orchestration via Transformers.js & WebGPU. Express/Electron hybrid for low-end hardware. Vision, TTS, STT, and Music Gene…☆22Jul 17, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI☆113,776Updated this week
- High-performance AI agent for long-horizon tasks and local models. Built on empirical research. 200k+ tokens of work inside a 64k context…☆443Updated this week
- CTX - Context Runtime Engine for Coding Agents☆144May 11, 2026Updated 4 months ago
- A markdown web renderer for AI agents — see the web without screenshots☆68Aug 28, 2026Updated last month
- ~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server☆647Updated this week
- Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, …☆34Oct 1, 2026Updated last week
- An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, a…☆3,409Updated this week
- MCP server for Git with local Ollama — zero tokens for git operations☆43Oct 2, 2026Updated last week
- Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.☆233Sep 6, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Explore the unknown, build the future, own your data.☆473Updated this week
- Why observe computer if computer can observe for you☆1,650Updated this week
- Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https…☆5,851Updated this week
- Token-saving companion for OpenCode — 42 compression layers, zero risk, no caveman speak☆165May 29, 2026Updated 4 months ago
- A web-based AI workspace with a local execution daemon, with an emerging control-plane architecture for remotely operating AI coworkers a…☆122Updated this week
- Air gapped, privacy focused open source NotebookLM alternative. Join our Discord: https://discord.gg/ejRNvftDp9☆16,340Updated this week
- A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows☆2,254Sep 1, 2026Updated last month