Alternatives
Products that do what FastRecall does
Context across AI models. Cheap and lightning fast.
- 1SU
Here's a project I've been working on for the last few months. It's a new (I think) algorithm, that allows to adjust smoothly - and in real time - how many calculations you'd like to do during inference of an LLM model. It seems that it's possible to do just 20-25% of weight multiplications instead of all of them, and still get good inference results. I implemented it to run on M1/M2/M3 GPU. The mmul approximation itself can be pushed to run 2x fast before the quality of output collapses. The inference speed is just a bit faster than Llama.cpp's, because the rest of implementation…
2024 · asciinema.org
- 2IB
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
- 3EL
2023 · github.com
- 4IR
Jul 2026 · github.com
- 5IP
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
Mar 2026 · georgelarson.me
- 6
- 7
- 8RG
Hey HN! I'm José, and I built Recall to solve a problem that was driving me crazy. The Problem: I use Claude for coding daily, but every conversation starts from scratch. I'd explain my architecture, coding standards, past decisions... then hit the context limit and lose everything. Next session? Start over. The Solution: Recall is an MCP (Model Context Protocol) server that gives Claude persistent memory using Redis + semantic search. Think of it as long-term memory that survives context limits and session restarts. How it works: - Claude stores important context as "memories" during…
Oct 2025 · npmjs.com
- 9
- 10
- 11TB
After training calculator agent via RL, I really wanted to go bigger! So I built RL infrastructure for training long-horizon terminal/coding agents that scales from 2x A100s to 32x H100s (~$1M worth of compute!) Without any training, my 32B agent hit #19 on Terminal-Bench leaderboard, beating Stanford's Terminus-Qwen3-235B-A22! With training... well, too expensive, but I bet the results would be good! *What I did*: - Created a Claude Code-inspired agent (system msg + tools) - Built Docker-isolated GRPO training where each rollout gets its own container - Developed a multi-agent…
2025 · github.com
- 12
- 13
An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory
24d ago · github.com
- 14AH
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
- 15RA
Hi HN, we are the founders of Relari (https://www.relari.ai). We launched our LLM evaluation stack on HN a few months ago (https://news.ycombinator.com/item?id=39641105), which is now used in production by AI teams at companies like Vanta and PwC. We have since expanded to directly optimizing parts of an LLM pipeline using a data-driven approach. In particular, we see a lot of potential in the Auto Prompt Optimization—which could be an attractive alternative to fine-tuning in many cases—to use data to align LLMs for domain-specific tasks. Here’s a demo video:…
2024
- 16RG
Hi HN! We're Giacomo and Roberto, authors of Ratel (https://github.com/ratel-ai/ratel) We used to help SaaS companies build agents on top of their products. Whenever we wanted to expand the agents’ complexity/scope, by adding more and more tools and instructions, we always run in the same issue: context bloat, with frequent hallucinations and sky high token bills. So we started constantly engineering the agents, dynamically loading tools, splitting them into subagents, inventing our own way to support skills And that's exactly when we started building Ratel: a…
Jul 2026 · github.com
- 17MM
Hi HN! We (Thomas and Stéphan, hello!) recently released Model2Vec, a Python library for distilling any sentence transformer into a small set of static embeddings. This makes inference with such a model up to 500x faster, and reduces model size by a factor of 15 (7.5M params or 15/30MB on disk, depending on whether you use float16 or float32). This allows you to embed 50-100k documents per second on a cpu on a macbook. This reduction of course comes at a cost: distilled models are worse than their parent models. Even so, they are actually a lot better than large sets of conventional…
2024 · github.com
- 18IR
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
- 19
- 20SR
Sep 2025 · arc.computer
- 21RA
Hey everyone! Along with my team, I've developed a reinforcement learning system that automatically optimizes LLM prompts, complete with a visualization feature to track both prompt structure and learning progress over time. Take a look here: https://nomadic-ml.github.io/nomadic/cookbooks/Nomadic_Promp... Check out our website too:https://www.nomadicml.com/ In terms of how this visualization works: The RL Prompt Optimizer employs a reinforcement learning framework to iteratively improve prompts used for language model evaluations. At each episode, the…
2024 · nomadic-ml.github.io
- 22ML
We’ve recently open-sourced Model2vec, a method to distill sentence transformers into static embeddings that outperform all previous approaches by a large margin on MTEB. Our new models set a new state-of-the-art for static embeddings. Main features: - Our best model (potion-base-8M) has only 8M parameters, which is ~30mb on disk - Inference is ~500x faster than the distilled base model (bge-base), on a CPU - New models can be distilled in 30 seconds on a CPU without requiring a dataset - just a vocabulary - Numpy-only inference: The packaged can be install the package with minimal…
2024 · github.com
- 23RA
While building my AI-powered dating app, I couldn't find a memory backend that was affordable,accessible and efficient. I built Redcache-ai to meet this need. Redcache-ai is also available as a Python package. Happy to receive feedback and answer questions. Note: I am not a native English speaker. Apologies for the typos and grammatical errors.
2024 · github.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →