Where boundaries are made to be pushed.
The experimental research branch of LibertAI — open weights, novel inference architectures and agent systems for the next generation of private, decentralized intelligence.
- 24k+
- downloads
- 9
- projects
- 9
- open repos
Model releases
Open weights, quantization notes and reproducible benchmark context.
Agent systems
Runtime experiments, evaluation harnesses and tool interfaces for private agents.
Infrastructure
Search, confidential compute and payment primitives that support the product stack.
Projects
Releases and research tracks
NVFP4 model releases
GGUF and safetensors builds of flagship open models with calibrated NVFP4 tensors, benchmarked honestly against stock K-quants on Blackwell hardware.
Read project →Consensus web search
A search API that queries Google, Bing and DuckDuckGo in parallel from Aleph Cloud's decentralized network and ranks results by cross-engine agreement.
Read project →LibertAI Code
A coding agent for the terminal and desktop that runs open models on confidential, TEE-backed inference, with no training on your code.
Read project →Conscio
The consciousness layer for LLM agents: persistent memory, attention, drives, self-monitoring, reflection, and autonomous action in one inspectable runtime.
Read project →MCP server
A Model Context Protocol server built into the CLI that gives Claude Code, Cursor, Cline and any other MCP client access to consensus web search.
Read project →Avatar
A browser avatar you can talk to, combining a 3D stage, browser speech APIs and LibertAI chat completions, with conversations kept in your browser.
Read project →GLM-5.3-Flash on vLLM, on GB10
A hand-written sparse-MLA CUDA kernel for sm_121 and a fix for vLLM's uninitialised NVFP4 MoE activation scale, which together take GLM-5.3-Flash from degenerate output to correct serving on a two-node DGX-Spark-class cluster.
Read project →Post-quantum blockchain security review
An adversarial review of 30 live networks, migration efforts, standards proposals and on-chain verifiers, with high-priority findings moving through responsible disclosure.
Read project →Open weights
Published on Hugging Face
Quantized builds of the open models we serve, published under LibertAIDAI with benchmark numbers in every model card. Counts are from June 2026.
View on Hugging Face ↗- repos
- 9
- downloads
- 24k+
- base models
- 5
Papers
Formal writeups
Full papers with related work, falsifications and precise claims.
Notes
Methodology and results
Writeups with methodology, the numbers that held up, and the ones that did not.