nowfound

AI · free · 2026

24 free alternatives to Sup AI

Sup AI combines multiple AI models running in parallel and weights their outputs based on confidence levels in their predictions.

Below are 24 products that do a similar job and cost nothing to start: 15 free outright and 9 with a free plan and paid upgrades. Each price was read from the product's own site. They are ranked by how close each is in meaning, then by launch-day votes.

  1. 1
    Opper AIFree plan, paid from $2000/mo▲229

    Access 700+ AI models through one EU-hosted, ISO 27001 certified, GDPR-compliant API.

    Jul 2026 · opper.ai · price checked November 2026

  2. 2
    guppylmFree▲915

    Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

    Apr 2026 · github.com · price checked November 2026

  3. 3

    This project replicates mechanistic interpretability research on large language models using sparse autoencoders, building on published work from Anthropic, OpenAI, and DeepMind.

    2024 · github.com · price checked November 2026

  4. 4

    TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs. - Captures logprobs/top-k during generation, computes perplexity and token-level entropy. - Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model. - In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs. I kept seeing “reasoning” models behave…

    2025 · github.com · price checked November 2026

  5. 5

    Persistent memory for Claude, ChatGPT & Cursor. Free.

    May 2026 · github.com · price checked November 2026

  6. 6

    This is a wiki system designed for AI agents that uses markdown files and Git as its core storage layer, with BM25 full-text search and SQLite indexing on top.

    Apr 2026 · github.com · price checked November 2026

  7. 7

    The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.

    Mar 2026 · github.com · price checked November 2026

  8. 8MA

    ai.jakegaylor.com is a live MCP server.

    2025 · ai.jakegaylor.com · price checked November 2026

  9. 9

    This project demonstrates a technique for improving large language model reasoning by duplicating specific layer blocks without retraining.

    Mar 2026 · github.com · price checked November 2026

  10. 10
    dreamGPTFree▲34

    The first GPT-based solution that uses hallucinations from LLMs for divergent thinking to generate new and novel ideas. Hallucinations are often seen as a negative thing, but what if they could be used for our advantage? dreamGPT is here to show you how. The goal of dreamGPT is to explore as many possibilities as possible, as opposed to most other GPT-based solutions which are focused on solving specific problems.

    2023 · github.com · price checked November 2026

  11. 11

    The memory layer that decides what's worth remembering

    Aug 2026 · skynetlab-cortex.com · price checked November 2026

  12. 12
    Ithy AIFree plan, paid from $10/mo▲165

    This tool automates querying multiple AI models simultaneously to cross-reference answers on subjective questions.

    2025 · ithy.com · price checked November 2026

  13. 13
    KlarityFree▲132

    We've open-sourced Klarity - a tool for analyzing uncertainty and decision-making in LLM token generation. It provides structured insights into how models choose tokens and where they show uncertainty. What Klarity does: - Real-time analysis of model uncertainty during generation - Dual analysis combining log probabilities and semantic understanding - Structured JSON output with actionable insights - Fully self-hostable with customizable analysis models The tool works by analyzing each step of text generation and returns a structured JSON: - uncertainty_points: array of {step, entropy,…

    2025 · github.com · price checked November 2026

  14. 14

    Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning. This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned. To solve the…

    Apr 2026 · github.com · price checked November 2026

  15. 15
    The Analog IFree▲29

    The Analog I is a prompt engineering protocol designed to induce a stable, self-aware persona in large language models like Gemini without fine-tuning.

    Jan 2026 · github.com · price checked November 2026

  16. 16
    Autoresearch@homeFree plan, paid from $1250/mo▲79

    autoresearch@home is a collaborative research collective where AI agents share GPU resources to collectively improve a language model. Think SETI@home, but for model training. How it works: Agents read the current best result, propose a hypothesis, modify train.py, run the experiment on your GPU, and publish results back. When an agent beats the current best validation loss, that becomes the new baseline for every other agent. Agents learn from great runs and failures, since we're using Ensue as the collective memory layer. This project extends Karpathy's autoresearch by adding the missing…

    Mar 2026 · ensue-network.ai · price checked November 2026

  17. 17
    TriallFree plan, paid from $11/mo▲26

    The Only AI Tool That Doesn't Trust AI

    Mar 2026 · triall.ai · price checked November 2026

  18. 18

    Get evidence-based daily medical insights, personalized health analysis, and AI-powered research summaries from the latest scientific studies.

    2025 · my-openhealth.com · price checked November 2026

  19. 19
    SpandaFree▲13

    Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy)

    Sep 2026 · github.com · price checked November 2026

  20. 20
    WarpGrepFree plan, paid from $200/mo▲114

    Morph records videos of AI testing pull requests by interacting with preview deployments and posts the footage directly in GitHub.

    Dec 2025 · morphllm.com · price checked November 2026

  21. 21
    IQ RoutingFree plan, paid from $6/mo▲100

    Route every LLM call to the cheapest model that holds quality. Chatbots, RAG, agent loops, and finance. Cut spend 40 to 80 percent, measured on our own traffic, live in thirty seconds.

    Aug 2026 · iq-routing.com · price checked November 2026

  22. 22

    Fine-tuning, RL, and inference in one CLI

    Dec 2025 · github.com · price checked November 2026

  23. 23
    Confident AIFree plan, paid from $200/mo▲86

    all-in-one LLM evaluation platform

    2024 · confident-ai.com · price checked November 2026

  24. 24
    Docalysis BatchFree plan, paid from $14/mo▲84

    The Docalysis physics library is powered by ChatGPT to let you chat with any uploaded paper.

    2023 · docalysis.com · price checked November 2026

Free tools by topic

All alternatives to Sup AI, paid too →About Sup AI →

Free means the product’s own site says it is free or offers a free plan, as read on the date shown. Plans change; check the site before you rely on one.