AI · alternatives · 2026

24 alternatives to Hillock: Local neuro-symbolic memory engine in <1.2GB VRAM

Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI. - roandejager/Hillock

Hillock is a local memory engine for artificial intelligence that runs offline with minimal computing resources, using less than 1.2GB of VRAM. It combines hyperdimensional computing, Hebbian plasticity, and… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.

1
LocalGPT – A local-first AI assistant in Rust with persistent memory▲331
I built LocalGPT over 4 nights as a Rust reimagining of the OpenClaw assistant pattern (markdown-based persistent memory, autonomous heartbeat tasks, skills system). It compiles to a single ~27MB binary — no Node.js, Docker, or Python required. Key features: - Persistent memory via markdown files (MEMORY, HEARTBEAT, SOUL markdown files) — compatible with OpenClaw's format - Full-text search (SQLite FTS5) + semantic search (local embeddings, no API key needed) - Autonomous heartbeat runner that checks tasks on a configurable interval - CLI + web interface + desktop GUI - Multi-provider:…
Feb 2026 · github.com · its alternatives →
2
ArcaneVM – A Fully Homomorphic Encryption Brainfuck Virtual Machine▲131
A Fully Homomorphic Encryption Brainfuck virtual machine - f-prime/arcanevm
2019 · github.com · its alternatives →
3
memories.sh▲50
One layer for memories, skills, and rules across any agent
Feb 2026 · memories.sh · its alternatives →
4
NeuroBlock▲120
No-code AI Lab: Train models, access datasets, run inference
Feb 2026 · neuro-block.com · its alternatives →
5
Khaos Brain▲72
Local predictive memory for AI agents
May 2026 · github.com · its alternatives →
6
Neuropod – Uber ATG's open source deep learning inference engine▲80
A uniform interface to run deep learning models from multiple frameworks - uber/neuropod
2020 · github.com · its alternatives →
7
I ran a language model on a PS2▲46
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 · its alternatives →
8
I evaluated file, vector, graph and RL based memory frameworks▲13
An agent that remembers across sessions can keep its memory as curated markdown files, as an auto-mined structured store, or as trained experience.
Aug 2026 · pinglin.tw · its alternatives →
9
IHMT – Infinite Hierarchical Memory Tree for AI Agents▲8
Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files - gonzaroman/IHMT-MEMORY
12d ago · github.com · its alternatives →
10
Shodh– AI memory that learns from use, no LLM calls, single Rust binary▲6
Hey HN, I built this because most AI memory solutions (mem0, Zep) need cloud connectivity. That doesn't work for drones flying beyond cell coverage or robots in warehouses. Shodh-Memory is a local-first AI memory system: - 100% offline, runs on edge devices - 4MB binary, sub-100ms retrieval - Multi-tier memory (working → session → long-term) - Geo-spatial queries for GPS-tagged memories - Mission tracking for autonomous systems Install: pip install shodh-memory Quick example: ```python from shodh_memory import MemorySystem memory = MemorySystem("./robot_memory") memory.record(…
Feb 2026 · github.com · its alternatives →
11
Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)▲21
Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining
Aug 2026 · github.com · its alternatives →
12
Mnemosyne Local hierarchical memory engine for AI agents (MCP Native)▲10
Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server. - M4F-S/gomaa
Aug 2026 · github.com · its alternatives →
13
ArcaneVM – A Fully Homomorphically Encrypted Brainfuck Virtual Machine▲7
A Fully Homomorphic Encryption Brainfuck virtual machine - f-prime/arcanevm
2021 · github.com · its alternatives →
14AN
A new engine to run Kimi K3 on a laptop▲7
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026 · its alternatives →
15
Anchor Engine – Deterministic Semantic Memory for LLMs Local (<3GB RAM)▲5
Anchor Engine is ground truth for personal and business AI. A lightweight, local-first memory layer that lets LLMs retrieve answers from your actual data—not hallucinations. Every response is traceable, every policy enforced. Runs in <3GB RAM. No cloud, no drift, no guessing. Your AI's anchor to reality. We built Anchor Engine because LLMs have no persistent memory. Every conversation is a fresh start—yesterday's discussion, last week's project notes, even context from another tab—all gone. Context windows help, but they're ephemeral and expensive. The STAR algorithm (Semantic Traversal And…
Mar 2026 · github.com · its alternatives →
16
SOTA long memory eval with open source models▲5
Cursor published a great post last week on scaling long-running autonomous coding agents to build a browser. We’ve been exploring a similar idea, but applied to math proofs We show how a swarm of agents, coordinated via shared memory, can generate a Lean proof for a non-trivial multi-step math problem-Putnan A2-that a single agent struggled with. We were feeling fancy so we wrote a full post and captured the runtime. Harness will be public soon(tm) for you to run it yourself.
Mar 2026 · ensue.dev · its alternatives →
17
Honcho – Open-source memory infrastructure, powered by custom models▲8
Hey HN, It’s Vineeth from Plastic Labs. We've been building Honcho, an open-source memory library for stateful AI agents. Most memory systems are just vector search—store facts, retrieve facts, stuff into context. We took a different approach: memory as reasoning. (We talk about this a lot on our blog) We built Neuromancer, a model trained specifically for AI-native memory. Instead of naive fact extraction, Neuromancer does formal logical reasoning over conversations to build representations that evolve over time. Its both cheap ( $2/M tokens ingestion, unlimited retrieval), token…
Jan 2026 · github.com · its alternatives →
18
Friday – Self-hosted persistent memory for AI coding agents (MCP)▲9
⚡ The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia. - itskie/friday
Sep 2026 · github.com · its alternatives →
19
MemoryCore – symbolic, peer-to-peer memory system for AI▲7
I’m not a software engineer or a genius — I just had a weird idea: What if memory wasn’t just stored as text or embeddings, but as symbolic, byte-level thoughts that could be passed between AIs? That idea became MemoryCore Lite: Encodes thoughts into lightweight bytecode Shares them across nodes via peer-to-peer sync Fully decentralized, no GPU needed Designed to evolve into its own AI knowledge mesh I just open-sourced the basic version here: github.com/ProToxicNinja/MemoryCore-Lite-Symbolic-Memory-Engine-for-AI It’s simple — but everything works. You can build better tokenizers,…
2025 · github.com · its alternatives →
20
OpenMemory▲9
Give AI agents long-term memory. Not vector search or RAG
Dec 2025 · github.com · its alternatives →
21
Serve 100 Large AI models on a single GPU with low impact to TTFT▲7
I wanted to build an inference provider for proprietary AI models, but I did not have a huge GPU farm. I started experimenting with Serverless AI inference, but found out that coldstarts were huge. I went deep into the research and put together an engine that loads large models from SSD to VRAM up to ten times faster than alternatives. It works with vLLM, and transformers, and more coming soon. With this project you can hot-swap entire large models (32B) on demand. Its great for: Serverless AI Inference Robotics On Prem deployments Local Agents And Its open source. Let me know if anyone…
Nov 2025 · github.com · its alternatives →
22
HAI 1.0 The 1.2GB AI that outcodes GPT5▲5
HAI 1.0: 1.2GB local AI. Beats GPT-5 at coding
Jul 2026 · github.com · its alternatives →
23
Hebbs – a single-binary memory engine for AI agents – sub-10ms▲6
Contribute to hebbs-ai/hebbs-memory-engine development by creating an account on GitHub.
Mar 2026 · github.com · its alternatives →
24
SuperLocalMemory V2▲4
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253 - qualixar/superlocalmemory
Feb 2026 · github.com · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →