Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data.
☆1,301Nov 5, 2026Updated this week
Alternatives and similar repositories for mini-AGI
Users that are interested in mini-AGI are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Sub-50mb agentic, voice and vision intelligence for consumer devices.☆14,499Updated this week
- Lossless long-term memory for a personal AI: never summarize, keep every line, put a timestamp on everything.☆168Sep 23, 2026Updated last month
- ☆479Oct 18, 2026Updated 2 weeks ago
- A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from…☆48,363Updated this week
- open-source canvas for thoughtful software design☆3,451Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Contrastive Language Models (CLMs) are a new class of System One model trained with a contrastive learning objective that connects states…☆3,166Oct 5, 2026Updated last month
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆40,925Updated this week
- Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Wo…☆7,719Updated this week
- A self-improving RLM agent for coding workflows and long-running autonomous tasks.☆22,608Updated this week
- Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ lan…☆35,100Updated this week
- Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.☆4,932Sep 23, 2026Updated last month
- 37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama…☆646Updated this week
- Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.☆510Updated this week
- Breaking the quadratic memory barrier in AI☆60Oct 13, 2026Updated 3 weeks 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.
- ☆1,368Sep 16, 2026Updated last month
- ☆22,908Updated this week
- Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own☆9,826Updated this week
- An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gem…☆492Oct 30, 2026Updated last week
- Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, …☆855Updated this week
- ☆1,729Sep 23, 2026Updated last month
- The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor…☆304Sep 26, 2026Updated last month
- Keep Python on your laptop. Run PyTorch operations and hold tensors on a remote GPU, including from a Mac with no CUDA installation.☆78Oct 22, 2026Updated 2 weeks ago
- A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine☆172Sep 21, 2026Updated last month
- 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.
- The open-source agent harness - the runtime layer that turns an LLM into a working agent.☆6,445Updated this week
- HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code…☆4,256Updated this week
- Train a tiny GPT in under a minute (CUDA only)☆56Oct 15, 2026Updated 3 weeks ago
- A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.☆10,864Oct 2, 2026Updated last month
- Multimodal visual memory search on macOS☆524Updated this week
- OpenShell is the safe, private runtime for autonomous AI agents.☆21,206Updated this week
- Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and…☆1,586Oct 21, 2026Updated 2 weeks ago
- The runtime for a personal assistant☆438Updated this week
- Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.☆31,867Updated 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.
- Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Window…☆9,113Updated this week
- RL-training an AI agent to RL-train AI agents.☆243Jul 14, 2026Updated 3 months ago
- Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more☆39,696Updated this week
- Jeeves – Reasoning improves Jev-like decision models☆433Oct 16, 2026Updated 3 weeks ago
- 🎯 CenterOS — The Lightweight AI Operating System! A simple, cloneable framework that turns your AI into a personalized system for automa…☆61Sep 1, 2026Updated 2 months ago
- Live-bending a foundation model’s output at neural network level.☆274Aug 30, 2026Updated 2 months ago
- Fastest and cheapest web agent☆24,235Updated this week