Search Results for "ofn-layer-modes"
Sort By:
186 projects for "ofn-layer-modes" with 2 filters applied:
-
Streamline Azure Security with Palo Alto Networks VM-SeriesImprove your security posture and reduce incident response time. Use the VM-Series to natively analyze Azure traffic and dynamically drive policy updates based on workload changes.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
1
OAGI Python SDK
Python SDK for the Computer Use model Lux, developed by OpenAGI
OAGI Python SDK is a Python client library for the Lux computer-use model that turns Lux into a programmable automation layer for operating human-facing software via vision and actions. It exposes the OAGI API in an ergonomic way, letting you trigger Lux in three main modes: Tasker for precise scripted sequences, Actor for fast one-shot tasks, and Thinker for open-ended, multi-step objectives. The SDK is designed around “computer use” as a paradigm, where the AI actually navigates interfaces, clicks, types, scrolls, and reads the screen through screenshots instead of only calling APIs. ... -
2
AirLLM
AirLLM 70B inference with single 4GB GPU
...The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. AirLLM preprocesses model weights so that each transformer layer can be loaded independently during computation, reducing the memory footprint while still performing full inference. As a result, developers can experiment with models that previously required specialized high-end GPUs. -
3
AxonHub
Use any SDK to call 100+ LLMs
AxonHub is an open-source AI gateway platform designed to simplify the process of integrating and switching between different large language model providers. The system acts as a compatibility layer that allows developers to use the same SDK interface while routing requests to various AI services behind the scenes. Instead of rewriting code when switching providers such as OpenAI or Anthropic, developers can simply change configuration settings within the gateway. AxonHub translates requests from one provider’s API format into another, enabling seamless interoperability across different AI platforms. ... -
4
BruteForceAI
Advanced LLM-powered brute-force tool combining AI intelligence
...From a software design perspective, its distinguishing idea is the use of language models as a front-end analysis layer that interprets a target page before the rest of the workflow proceeds. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
BoxMOT
Pluggable SOTA multi-object tracking modules for segmentation
...It also includes evaluation tools and benchmarking pipelines that allow researchers to test tracking performance on standard datasets such as MOT17 and MOT20. The system offers different performance modes that balance computational efficiency with tracking accuracy depending on the application requirements. -
6
Poco Claw
A more beautiful and easier-to-use alternative to OpenClaw
...The system operates on a sandboxed runtime, ensuring that tasks executed by the agent are isolated from the host environment, which improves security and reliability. It extends beyond simple chatbot functionality by supporting structured workflows, task planning modes, and multi-step execution pipelines. The platform also allows users to manage files and contexts directly within the interface, enabling more complex interactions with data and projects. It is built to make AI agent systems accessible to a broader audience, including users who may not be comfortable with command-line environments. -
7
Pinchtab
High-performance browser automation bridge and orchestrator
...It launches and manages its own Chrome instance while remaining framework-agnostic, so it can be used with any language or agent system. Pinchtab also supports persistent sessions, stealth automation, and both headless and headed operation modes. The project’s goal is to provide fast, cheap, and portable browser control infrastructure for modern AI workflows. -
8
Attention Residuals (AttnRes)
Drop-in replacement for standard residual connections in Transformers
...In standard transformers, residual connections simply sum outputs from previous layers, which can lead to uncontrolled growth of hidden states and dilution of early-layer information in deep networks. Attention Residuals introduces a learnable softmax attention mechanism that allows each layer to selectively retrieve and weight useful representations from earlier layers, making depth dynamically adaptive rather than uniformly aggregated. This approach improves gradient stability, preserves meaningful signals throughout the network, and enhances performance in reasoning-heavy tasks such as coding, mathematics, and multi-step problem solving. -
9
MemMachine
Universal memory layer for AI Agents
MemMachine is a universal memory layer designed for AI agents that provides persistent, rich memory storage and retrieval capabilities so autonomous agent systems can recall context, personal preferences, and long-term interaction history across sessions, models, and use cases. Unlike ephemeral LLM prompt state, MemMachine supports distinct memory types—short-term conversational context, long-term persistent knowledge, and profile memory for personalized facts—persisted in optimized stores (e.g., graph databases for episodic lines of reasoning and SQL for user facts) to support robust, context-aware intelligence in agents. ... -
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
10
Byterover Cipher
Byterover Cipher is an opensource memory layer
Cipher is an open-source infrastructure component designed to provide a persistent memory layer for AI coding agents and developer tools. The system captures contextual information about codebases, past interactions, and reasoning steps generated by AI assistants so that agents can maintain long-term context while generating code. By storing structured knowledge about programming concepts, project logic, and previous development sessions, Cipher allows AI agents to operate with improved awareness of the software environment they are working within. ... -
11
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
...The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. GLM-4.5 achieves strong performance on 12 industry-standard benchmarks, ranking 3rd overall, while GLM-4.5-Air balances competitive results with greater efficiency. ... -
12
Sprite Fusion Pixel Snapper
A tool to snap pixels to a perfect grid
...SpriteFusion Pixel Snapper integrates with popular game engines and rendering pipelines to ensure that assets remain sharp across a broad range of resolutions and aspect ratios without requiring manual fiddling from artists or developers. It includes options for snapping modes, filtering overrides, and automatic correction detection that can be applied on export or at runtime. -
13
OpenSpec
Spec-driven development (SDD) for AI coding assistants
OpenSpec is a lightweight specification layer designed to improve reliability when working with AI coding assistants by formalizing requirements before code generation begins. The project addresses the common issue where AI tools produce inconsistent results when specifications exist only in chat history. It introduces a structured workflow that encourages teams to agree on what should be built before implementation starts. -
14
MiniCPM4.1
Achieving 3+ generation speedup on reasoning tasks
MiniCPM4.1 is an enhanced iteration of the MiniCPM4 architecture, introducing improvements in reasoning capabilities, inference speed, and hybrid operation modes that allow dynamic switching between deep reasoning and standard generation. It builds upon the same efficiency-focused philosophy but further optimizes decoding performance, achieving substantial speed gains in reasoning-intensive tasks while maintaining high-quality outputs. One of its key innovations is the hybrid reasoning mode, which allows developers to control whether the model engages in deeper reasoning processes or faster responses depending on the use case. ... -
15
slime LLM
slime is an LLM post-training framework for RL Scaling
...It offers a flexible architecture that connects high-throughput training (e.g., via Megatron-LM) with a customizable data generation pipeline, enabling researchers and engineers to iterate on new RL training paradigms effectively. The framework is designed to support a wide range of training modes, allowing both synchronous and asynchronous RL workflows and programmable rollout interfaces that simplify experimentation with custom environments and reward signals. Because it integrates tightly with SGLang and other training engines, slime can improve scalability and efficiency while providing maintainability and adaptability for developing new models and training algorithms. -
16
adversarial-spec
A Claude Code plugin that iteratively refines product specifications
adversarial-spec is a framework focused on designing and testing systems using adversarial thinking to uncover weaknesses and improve robustness. It encourages developers to define specifications that anticipate failure modes, edge cases, and malicious inputs before implementing solutions. The project emphasizes proactive design, ensuring that systems are built with resilience in mind from the beginning. It provides structured approaches for identifying vulnerabilities and stress-testing assumptions. The framework can be applied across domains, including software development, AI systems, and security workflows. ... -
17
Elia
Terminal-based LLM chat tool with multi-model and local support
...Users can chat with both proprietary models like ChatGPT and Claude, as well as local models such as Llama 3, Mistral, and Gemma. Elia stores conversations in a local SQLite database, making it easy to revisit past interactions. It supports flexible usage with inline and full-screen chat modes, along with simple configuration through a single file. Installation is straightforward via pipx, and users can customize themes, system prompts, and model settings. Elia is built for developers and power users who prefer a streamlined, terminal-first workflow for working with AI models. -
18
Embabel Agent Framework
Agent framework for the JVM. Pronounced Em-BAY-bel
...Built on top of the Spring ecosystem, it integrates seamlessly with enterprise infrastructure, enabling features like dependency injection, persistence, and transaction management. The framework supports multiple execution modes, including focused, closed, and open systems, each offering different levels of autonomy and flexibility. -
19
OpenWork
An open-source alternative to Claude Cowork, powered by opencode
OpenWork is a framework for building decentralized collaborative work environments powered by AI and human contributions. At its core, the project enables contributors to define tasks, workflows, and goals that can be split, shared, and recombined across distributed nodes while agents and humans cooperate to advance progress. It offers structured templates for work items, decision logic for task allocation, and consensus mechanisms that let groups verify and validate results toward shared... -
20
Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion
...It targets heavy users and researchers who push large models, control nets, and high-resolution pipelines where default settings can become bottlenecks. The fork typically introduces toggles for scheduler behavior, attention implementations, caching, and precision modes to reach better speed or quality on given hardware. It also focuses on stability during long sessions, aiming to reduce out-of-memory failures and provide clearer diagnostics when they occur. The UI surfaces advanced options in a way that remains recognizable to WebUI users, so migration costs are low while gaining experimental features. ... -
21
RealtimeSTT
A robust, efficient, low-latency speech-to-text library
RealtimeSTT is a Python-based realtime speech-to-text engine emphasizing low latency, wake-word detection, voice activity detection, and automatic speech segmentation. It provides asynchronous callbacks, nanosecond-precision timestamps, and CLI tools, suitable for building voice assistants, meeting transcribers, or live caption systems. -
22
llmfit
157 models, 30 providers, one command to find what runs on hardware
llmfit is a terminal-based utility that helps developers determine which large language models can realistically run on their local hardware by analyzing system resources and model requirements. The tool automatically detects CPU, RAM, GPU, and VRAM specifications, then ranks available models based on performance factors such as speed, quality, and memory fit. It provides both an interactive terminal user interface and a traditional CLI mode, enabling flexible workflows for different user... -
23
InsForge
InsForge is the backend built for AI-assisted development
...Rather than forcing developers to manually cobble together authentication flows, database schemas, storage buckets, and cloud functions, InsForge provides a semantic layer and toolchain that let agents configured with Model Context Protocol (MCP) understand the backend state, available operations, and how to manipulate these resources end to end. This enables AI coding assistants to complement human engineers by self-configuring backend components, connecting services, and evolving apps autonomously from prompts without switching contexts or manually provisioning infrastructure. -
24
Aix-DB
Based on the LangChain/LangGraph framework
...The platform supports multiple types of data sources and provides an end-to-end pipeline that includes intent recognition, SQL generation, database execution, and visual presentation of results. Its architecture includes multiple layers such as a web interface, API gateway, AI service layer, and data storage layer that support relational databases, vector stores, graph databases, and file systems. -
25
Shadcn UI v4 MCP Server
A mcp server to allow LLMS gain context about shadcn ui component
...It includes smart caching and efficient GitHub API usage to optimize performance and handle rate limits during component retrieval. The system also supports multiple transport modes such as standard input/output and Server-Sent Events, enabling both local and distributed deployments.