Search Results for "routing"
Sort By:
Showing 13 open source projects for "routing"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
...It divides computation into three main stages, including a pre-processing phase, a looped recurrent reasoning block, and a final output refinement stage, creating a structured pipeline for inference. The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. It is highly configurable through a centralized configuration system, allowing experimentation with different architectural parameters such as loop depth, attention type. -
2
Laya
Non-autoregressive System 1 decision engine
...It can run locally on CPU or GPU hardware and includes Python and TypeScript tooling. Integrations are available for HTTP, MCP, LangChain, LangGraph, LlamaIndex, CrewAI, and ONNX workflows. Laya is intended for fast classification, routing, triage, scoring, and other structured decisions where predictable outputs are more useful than generated prose. -
3
gemini-web2api
Convert Google Gemini web into OpenAI-compatible API
...The project can run as a simple local server and uses a mostly single-file design with an optional dependency for streaming. It supports model aliases for Flash, Thinking, Pro-style routing, Auto, and Lite variants. The tool also includes optional API keys, function calling, SSE streaming, web search access, Docker deployment, and client examples for OpenAI SDK-style usage. It is useful for developers who want local experimentation with OpenAI-compatible tooling while routing requests through Gemini web behavior. -
4
Laya-MLX
Native MLX runtime for Laya typed decision models
...Its implementation moves the encoder, decision transformer, scoring head, and action head into MLX. The project reports short-decision latency in the single-digit to low-teens millisecond range on an M3 Max, depending on the checkpoint. It also includes routing utilities, demos, validation tests, benchmarks, and a Python API. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
Claude Relay Service
Claude Code image, a one-stop open source transit service
...The project is designed to help users centralize subscriptions and API usage for services such as Claude, OpenAI, Gemini, and related tools. It acts as a middleware layer that forwards requests while managing authentication, routing, and cost-sharing scenarios. The system is particularly useful for teams or communities that want to pool access or simplify integration with different AI backends. Its architecture supports compatibility with native client tools so existing workflows can continue to function without major modification. Overall, claude-relay-service functions as a flexible AI access hub for consolidating multi-provider model usage. -
6
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
...It keeps the shared model trunk in memory and streams only the experts selected for each token from fast NVMe storage. A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has no third-party runtime dependency on its CPU inference path and exposes both a CLI and C library. An optional server provides an OpenAI-compatible chat API with streaming, tools, structured output, and image support. ... -
7
Kimi-K3
Open Frontier Intelligence
...It uses a 2.8-trillion-parameter mixture-of-experts architecture while activating 104 billion parameters per token. Its design combines Kimi Delta Attention, gated multihead latent attention, Attention Residuals, and Stable LatentMoE routing. The model can process text and images and supports a context window of more than one million tokens. It is built for long engineering sessions, large repository navigation, tool orchestration, research, visualization, and other extended tasks. The repository publishes the model overview, technical report, evaluation results, architecture specifications, and open weights under the Kimi K3 License. -
8
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
...The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. With its high-dimensional attention mechanisms and expert routing, Kimi-K2 excels across benchmarks in live coding, math reasoning, and problem solving. -
9
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
MiniMax-01 is the official repository for two flagship models: MiniMax-Text-01, a long-context language model, and MiniMax-VL-01, a vision-language model built on top of it. MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel strategies such as LASP+, varlen ring attention, and Expert Tensor Parallelism, enabling a training context of 1 million tokens and up to 4 million tokens at inference. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
Warlock-Studio
AI Suite for upscaling, interpolating & restoring images/videos
v6.0. Warlock-Studio is a Windows application that uses Real-ESRGAN, BSRGAN, IRCNN, GFPGAN, RealESRNet, RealESRAnime and RIFE Artificial Intelligence models to upscale, restore faces, interpolate frames and reduce noise in images and videos. the application supports GPU acceleration (including multi-GPU setups) and offers batch processing for large workloads. It includes drag-and-drop handling for single or multiple files, optional pre-resize functions, and an automatic tiling system... -
11
ChatGPT Clone
ChatGPT interface with better UI
...The project is useful for prototyping assistants, documentation bots, and internal developer tools without committing to a specific vendor or UI framework. Configuration is kept simple so newcomers can get a working chat in minutes and then dial in features like authentication or multi-model routing. While it illustrates how to hook into third-party LLM endpoints, it is typically positioned as an educational, self-hosted starter that you should operate responsibly and within provider's terms of use. -
12
ZAYA1-8B
Efficient MoE reasoning model for coding and math workloads
...ZAYA1-8B is optimized for long-form reasoning and test-time compute workflows, making it particularly effective for mathematical problem solving, coding tasks, and advanced reasoning chains. It introduces architectural innovations such as Compressed Convolutional Attention, a novel MLP-based expert router, and learned residual scaling to improve routing stability and inference efficiency. The model was trained entirely on AMD infrastructure and refined through supervised fine-tuning and multi-stage reinforcement learning focused on reasoning and coding. -
13
pplx-decider-v1-27b
Open 27B decision model for classification and probability estimation
...The model supports Choice decisions for multiclass classification and Noul decisions for yes/no judgments, returning calibrated probabilities that help applications evaluate confidence. It is designed for intent detection, request routing, factual verification, content moderation, document analysis, and automated decision workflows. Across 11 classification and reasoning benchmarks, it achieved 85.71% average accuracy, compared with 74.76% for its base model. Released under Apache 2.0, it supports local Python inference on CUDA GPUs with approximately 49 GiB of memory for model weights, plus additional working memory.
- Previous
- You're on page 1
- Next
