Loading...
Loading...
Magnitude: Open source inference server for local models. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Magnitude. This is an automatic list. We have not written a researched verdict for Magnitude yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Observability and Governance for AI-Generated Python scripts.
BotCity is a governance platform for Python in enterprises, built on the premise that when business users and AI agents automate work, they increasingly do it by writing and running Python scripts. It gives security, IT and automation teams visibility and control over that code, from scripts generated on employee lapto...
Automation Foundation Models For Tiny Devices
Cactus Compute builds very small foundation models that run locally on devices, led by Needle, now in its third version. Needle is a single 8 to 29 MB binary that trades general chat ability for reliable automation: given the functions an app exposes, it chooses the right tool calls and fills their arguments from what ...
The fastest & most scalable graph-vector database on the market
HelixDB is a database built for AI memory. It combines a property graph with native vector search and full text search in a single Rust engine running on object storage, so an application can traverse relationships and then run semantic or keyword search over the records it reaches, all in one request, instead of stitc...
The Javascript framework for building AI agents, from the Gatsby devs
Mastra is an open source TypeScript framework for building AI agents and AI powered applications. It gives developers agents that use LLMs and tools to work toward a goal, durable multi step workflows with typed control flow, memory that persists conversation context and application state across sessions, and a harness...
Fastest inference anywhere: open models on-prem, hosted or on-device
RunAnywhere is an inference company that spans hosted models, on device acceleration and developer SDKs. Its hosted product, Wally, serves frontier scale open models behind an OpenAI compatible API. Sign in happens in the browser, and the vendor states that hosted execution is always explicit: a request leaves the mach...
Open-Source Reinforcement Learning (RL) & Fine-tuning for LLMs.
Unsloth is an open source project for running and training AI models locally. Its current headline product is Unsloth Desktop, described as the first desktop app to run and train models that is open source, free and fully local. It is offered for Mac, Windows and Linux as a downloadable installer, alongside a Models se...