Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise

Tools tagged with "LLM"

Favicon of RocketRide

RocketRide

Free ListingStars: 18.8K

Open-source AI pipeline engine for LLM workflows

Agent Frameworks

RocketRide is an open-source AI pipeline engine with a C++ core and Python-extensible nodes. Build, debug, observe, and deploy LLM workflows and agent orchestration from the IDE using TypeScript and Python SDKs, with Docker deployment.

Favicon of LMCache

LMCache

Free ListingStars: 12.3K

KV cache management layer for scalable LLM inference

Context Management

LMCache is an open-source KV cache management layer for LLM inference that stores, compresses, searches, and reuses KV cache across GPU, CPU, local storage, and external backends to reduce repeated prefill and improve time-to-first-token.

Favicon of GhidraMCP

GhidraMCP

Free ListingStars: 11.7K

MCP server for Ghidra reverse engineering

MCP Servers & Tool Connectors

GhidraMCP is a Model Context Protocol server that exposes Ghidra tools to MCP clients, enabling LLMs to autonomously decompile and analyze binaries, rename methods and data, and list methods, classes, imports, and exports.

Favicon of OpenUI

OpenUI

Free ListingStars: 11.4K

Open Standard for Generative UI

App & UI Generation

OpenUI is the open standard for generative UI that lets AI apps and agents respond with interactive UI, charts, tables, forms, and dashboards using OpenUI Lang, a compact streaming-first language.

Favicon of Edge0

Edge0

Free ListingStars: 11K

Device-native foundation models for on-device AI

Language Models

Edge0 provides device-native foundation models and an open-source streaming MoE inference framework, running large sparse models such as 145B on a laptop and 35B on a phone with SSD-streamed weights, offline on-device processing, and zero

Favicon of InkOS

InkOS

Free ListingStars: 10.9K

AI agent for novels, scripts, and interactive games

Agent Frameworks

InkOS is an open-source story creation AI agent for long and short fiction, scripts, interactive games, IP content, and translation. Studio, TUI, and CLI share one workspace for settings, characters, memory, review, revision, covers, and

Favicon of Kev

Kev

Free ListingStars: 9.6K

Small Jev-like decision models to train and run yourself.

Language Models

Kev is a family of small decision models built on Qwen3.5 and Qwen3.8, based on Jev's architecture. Use pretrained weights or train your own, with yes/no, multiple-choice, and rating questions in one request.

Favicon of DeepInfer

DeepInfer

Free ListingStars: 7.9K

High-performance inference framework for DeepSeek models

Inference Servers & APIs

DeepInfer is a high-performance, large-scale inference framework for DeepSeek models. This open-source release provides offline inference with optimized kernels, parallelism, scheduling, deterministic sampling, and structured outputs.

Favicon of agentgateway

agentgateway

Free ListingStars: 5.8K

High-performance gateway for service, LLM, and MCP traffic.

MCP Servers & Tool Connectors

Open source HTTP and gRPC gateway that unifies traditional service traffic with AI-native protocols, routing, securing, observing, and governing LLM providers, MCP tools, and agent-to-agent communication in one data plane.

Favicon of Harbor

Harbor

Free ListingStars: 5.6K

Evaluate and optimize sandboxed agents and models.

Agent Frameworks

Harbor is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models in container environments. It supports arbitrary agents, custom benchmarks, parallel cloud experiments, and rollouts for RL

Favicon of llm-d

llm-d

Free ListingStars: 4.9K

Kubernetes-native distributed LLM inference

Model Gateways & Routing

llm-d is an open-source, Kubernetes-native stack for distributed LLM inference. It runs vLLM, SGLang, and more across a cluster, turning single-node engines into production-grade serving on existing hardware.

Favicon of AiSOC

AiSOC

Free ListingStars: 4.4K

Open-source, self-hostable AI security operations center

MCP Servers & Tool Connectors

AiSOC is an open-source, self-hostable AI SOC platform. It fuses alerts, triages incidents with LLM agents, maps MITRE ATT&CK, logs decisions in a replayable ledger, and ships CI-gated eval harness and MCP server. MIT-licensed, no API keys.

Favicon of Wenyi

Wenyi

Free ListingStars: 2.8K

Bring literature into your language with whole-book context.

Writing & Knowledge Work

Wenyi is a desktop app for translating books and long-form writing, combining whole-book understanding, consistent terminology, and evidence-based review to carry stories across languages.

Favicon of billion-context

billion-context

Free ListingStars: 1.7K

Context-compression plugin for long coding sessions

Context Management

billion-context is a context-compression plugin that lets agents work with small context windows, use about 5x fewer tokens, and sustain month-long single sessions handling billions of tokens.

Favicon of TensorFold

TensorFold

Free ListingStars: 1.5K

Native local LLM inference for Metal and CUDA.

Edge & On-Device Inference

TensorFold is an open-source LLM inference engine for Metal, CUDA, and Vulkan that runs open models locally on Apple Silicon and NVIDIA GPUs with native Metal and CUDA inference.

Favicon of neuron-explorer

neuron-explorer

Free ListingStars: 1.3K

Steering-first neuron explorer for Qwen3.5-4B

Language Models

A steering-first explorer for Qwen3.5-4B that pushes every MLP neuron, keeps every rollout, and lays the results out over a 3D view of the model.

OpenFree logo

Sand3D

Free ListingStars: 1.2K

3D modeling in Python, built for LLMs.

Datasets, Labeling & Data Quality

Sand3D is an open-source 3D-as-code library and dataset of 3D objects written in an LLM-friendly language. Each object is a Python program describing its parts, shapes, holes, positions, and materials.

Favicon of ZeroLeaks

ZeroLeaks

Free ListingStars: 0.7K

Continuous red teaming for AI agents

Security Testing & Red Teaming

ZeroLeaks offers security testing for AI agents and LLM prompts. Hosted continuous red teaming attacks agents through tools, memory, credentials, and connected agents; the source-available CLI and TypeScript library test standalone prompts.

Favicon of Hy-Memory

Hy-Memory

Free ListingStars: 0.3K

Dual-system cognitive memory for self-evolving LLM agents.

Agent Memory

Production-grade dual-system cognitive memory engine and Python SDK for self-evolving LLM agents, with dedicated Chat, Working, and Coding memory pipelines, plus MemHub for local-first cross-application recall.

Ad
OpenFree logoPromote your product

Reach more potential users and drive product growth and revenue.

Advertise