Search Results for "routing"
Sort By:
Showing 46 open source projects for "routing"
View related business solutions-
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.
-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
1
OpenSquilla
Token-Efficient AI Agent with same budget, higher intelligence density
...It includes persistent memory, built-in web search, on-device embeddings, and sandboxing for safer execution. OpenSquilla is designed for users who want stronger agent capabilities without wasting tokens on every interaction. Its main value is combining cost-aware routing, durable context, and multi-channel agent execution in one local runtime. -
2
Sprix SAGE Router
State-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks
Sprix SAGE Router is an open-source routing layer for coordinating agents in Agent2Agent networks. It decides whether an active agent should continue alone, recruit collaborators, or hand a task to another specialist. Routing decisions account for current progress, capability coverage, context-transfer costs, permissions, budgets, and deadlines. The system assigns remaining requirements to agents through task dependency graphs and estimates execution schedules. -
3
caveman
Why use many token when few token do trick
...The project often serves as a foundation for developers who want to build applications quickly without being constrained by heavy conventions or extensive configuration. It may include utilities for routing, state handling, or simple server logic, depending on its implementation scope. Caveman embraces a philosophy of “less is more,” encouraging developers to focus on core functionality rather than framework overhead. Its design makes it particularly useful for experimentation, small tools, or proof-of-concept applications. -
4
litelm
litellm without the bloat
litelm is a lightweight Python library that preserves the core routing and message-translation behavior of LiteLLM without its larger proxy and infrastructure layers. It supports provider/model routing, streaming, embeddings, text completions, tool calling, and the OpenAI Responses API. The package mirrors LiteLLM function names and response shapes so existing code can often switch with only an import change. -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
MSA, or Memory Sparse Attention, is a research framework for scaling language-model memory to extremely long contexts. It replaces full attention over all tokens with sparse selection of compressed latent memory states. Document-wise rotary position encoding and top-k routing keep training and inference close to linear complexity. A tiered KV-cache design stores routing keys on GPU while larger content states can remain on CPU. Its Memory Parallel engine distributes scoring and transfers only selected memory back to the accelerator. Memory Interleave alternates retrieval, context expansion, and generation to improve multi-hop reasoning across distant segments. ... -
6
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. -
7
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. -
8
Experiential
Experiential is the open source, zero markup gateway for BYOK
...The platform controls which users and agents can access specific models and how much they can spend. It collects execution traces to evaluate model performance, costs, and response speed. Developers can optimize custom routing strategies using real agent traffic and simulation workflows. It also supports fine-tuning specialized open-source models based on collected interactions. Experiential integrates with coding agents such as Claude Code, Codex, and Cursor and provides configurable telemetry, access controls, and local deployment options. -
9
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. -
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
10
Raven
Self-evolving multi-agent ecosystem for all-domain collaboration
...The system can generate task graphs, delegate work, combine results, and evolve tools, skills, and workflows over time. Raven supports a terminal interface, web UI, plugins, provider routing, and self-hosted deployment. It is designed for complex, long-horizon work that benefits from collaboration among agents with different strengths. -
11
VoiceStudio
VoiceStudio is the open-source, fully-local ElevenLabs alternative
VoiceStudio is an open-source, local-first platform for speech generation, voice cloning, transcription, dubbing, and audio production. It can clone voices from short reference recordings or design new voices from characteristics such as accent, pitch, age, and delivery style. Video dubbing combines transcription, translation, speaker preservation, speech synthesis, and final video export. It also supports multi-voice stories, audiobooks, dictation, vocal isolation, and speaker diarization.... -
12
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. -
13
Oh My Hermes
All in one plugin for Hermes Agent
Oh My Hermes is an operating layer for Hermes Agent that adds structured routing, coding workflows, long-term memory, and evidence-aware execution. It keeps Hermes as the conversational front end while deciding which workflow, model category, and specialist capability should handle each task. Work can be split into parallel lanes with isolated worktrees and typed completion states. The plugin includes a reviewed memory system that stores approved records with provenance and aging rules. ... -
14
FuXi
FuXi is a fast, self-contained AI coding agent
...Built in Go, it ships as a self-contained static binary with no runtime dependencies. Its agent loop follows a Think, Act, and Verify pattern so models can reason about a task, make changes, and check the results. It supports cost-aware routing and automatic failover across multiple LLM providers, including OpenAI-compatible services and other supported backends. More than 50 built-in tools cover file operations, shell access, search, diagnostics, Jupyter, browser use, background tasks, and parallel sub-agents. Sessions are persistent, extensible through MCP, hooks, skills, and plugins, and protected by command classification, permissions, and audit logging. -
15
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
...Instead of forcing each token to attend to every other token in the sequence, MoBA divides the context into blocks and dynamically routes queries to only the most relevant segments of information. This routing strategy reduces the computational cost associated with traditional attention while preserving performance on reasoning and long-context tasks. The approach allows language models to scale to significantly longer input contexts without the quadratic computational cost normally associated with transformer attention mechanisms. -
16
Claude Cognitive
Persistent context and multi-instance coordination
...It introduces an attention-based context router that prioritizes files and content relevant to the current development discussion — tagging them as HOT, WARM, or COLD based on recency and keyword activation — so Claude Code doesn’t waste token budget rereading irrelevant code. This context routing dramatically reduces redundant token usage and accelerates large codebase interactions by focusing only on what truly matters to the current task. Additionally, Claude-Cognitive includes a pool coordinator to share state across multiple Claude Code instances, preserving what’s been learned or completed and preventing repetitive debugging or redundant exploration. -
17
NVIDIA cuOpt
GPU accelerated decision optimization
NVIDIA cuOpt is a GPU-accelerated optimization engine designed to solve complex mathematical optimization problems at large scale. It supports a range of optimization models including linear programming (LP), mixed integer linear programming (MILP), quadratic programming (QP), and vehicle routing problems (VRP). Built primarily in C++, cuOpt leverages NVIDIA GPUs to deliver near real-time solutions for optimization tasks involving millions of variables and constraints. The platform provides multiple interfaces, including C, Python, and server APIs, allowing developers to integrate optimization capabilities into applications and services. cuOpt is designed for high-performance environments and can be deployed across cloud, hybrid, or on-premise infrastructures. ... -
18
DreamO
A Unified Framework for Image Customization
...Built on a diffusion-transformer (DiT) backbone, it supports a diverse set of tasks — including identity preservation, virtual “try-on” (e.g. clothing, accessories), style transfer, IP adaptation (objects/characters), and layout/condition-aware customizations — all handled within the same unified architecture. DreamO’s design introduces a feature routing constraint that helps disentangle different control conditions (like identity, style, clothing) when more than one is specified, which significantly reduces conflicts and artifacts when combining controls. It also uses a “placeholder strategy” to precisely align conditional inputs (e.g. where to place clothing or objects) in generated images, giving users fine-grained control over composition. -
19
Gpt-Agreement-Payment
End-to-end protocol replay toolkit for ChatGPT Plus/Team/Pro sub
Gpt-Agreement-Payment is a research-oriented automation toolkit focused on subscription payment flows, protocol replay behavior, and anti-fraud mechanism analysis. It documents and implements controlled workflows around account setup, payment routing, runtime state storage, and operational monitoring. The project includes both command-line and web UI modes, with Docker and manual deployment options. It stores runtime output and logs in a local SQLite-backed structure for review and debugging. Because it touches payment systems, account workflows, and fraud controls, it should be treated strictly as a research and compliance-sensitive project, not as a general-purpose automation product. ... -
20
PRINTFILM
AI video customer acquisition and AI short drama creation platform
...FFmpeg handles final composition, while background scheduling keeps generation jobs running after users leave a page. The platform includes an administration panel, model routing, an external API, and Docker deployment. -
21
Pruna AI
Pruna is a model optimization framework built for developers
Pruna is an open-source, self-hostable AI inference engine designed to help teams deploy and manage large language models (LLMs) efficiently across private or hybrid infrastructures. Built with performance and developer ergonomics in mind, Pruna simplifies inference workflows by enabling multi-model orchestration, autoscaling, GPU resource allocation, and compatibility with popular open-source models. It is ideal for companies or teams looking to reduce reliance on external APIs while... -
22
ContextForge MCP Gateway
A Model Context Protocol (MCP) Gateway & Registry
MCP Context Forge is a feature-rich gateway and registry that federates Model Context Protocol (MCP) servers and traditional REST services behind a single, governed endpoint. It exposes an MCP-compliant interface to clients while handling discovery, authentication, rate limiting, retries, and observability on the server side. The gateway scales horizontally, supports multi-cluster deployments on Kubernetes, and uses Redis for federation and caching across instances. Operators can define... -
23
Harness Engineering
Field guide, and agent context bundle for harness engineering
Harness Engineering is a retrieval-optimized anthology, field guide, and agent context bundle for improving AI coding-agent performance. It treats the model and agent as fixed while strengthening the surrounding context, tools, constraints, and proof mechanisms. The repository organizes developed arguments, practical cases, source evidence, evaluations, and reusable playbooks into distinct layers. Its agent guide routes each task to the smallest relevant set of materials instead of loading... -
24
Lingua-Py
The most accurate natural language detection library for Python
...This is very useful as a preprocessing step for linguistic data in natural language processing applications such as text classification and spell checking. Other use cases, for instance, might include routing e-mails to the right geographically located customer service department, based on the e-mails' languages. Language detection is often done as part of large machine learning frameworks or natural language processing applications. In cases where you don't need the full-fledged functionality of those systems or don't want to learn the ropes of those, a small flexible library comes in handy. -
25
AgentScope
Build and run agents you can see, understand and trust
AgentScope is a production-ready agent framework designed to help developers build, deploy, and scale intelligent agentic applications. It provides essential abstractions that evolve with advancing LLM capabilities, emphasizing reasoning, tool use, and flexible orchestration rather than rigid prompt constraints. With built-in support for ReAct agents, memory, planning, human-in-the-loop control, and real-time voice interaction, developers can create powerful agents in minutes. AgentScope...
