Search Results for "budgets"
Sort By:
Showing 16 open source projects for "budgets"
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.
-
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.
-
1
dsh-our-free-model
Simply install this plugin in your dsh
...The plugin can expose models through an OpenAI-compatible local endpoint for use by other software. It includes model availability checks, regional-status handling, configurable reasoning budgets, and local performance measurements. A dashboard tracks tokens, latency, generation speed, success rates, and recent requests while keeping usage statistics on the local machine. Built-in updating supports integrity checks, rollback, and hot reload. The project advertises several no-key model channels, although availability, privacy terms, and access conditions ultimately depend on the upstream providers. -
2
FastViT
This repository contains the official implementation of research
FastViT is an efficient vision backbone family that blends convolutional inductive biases with transformer capacity to deliver strong accuracy at mobile and real-time inference budgets. Its design pursues a favorable latency-accuracy Pareto curve, targeting edge devices and server scenarios where throughput and tail latency matter. The models use lightweight attention and carefully engineered blocks to minimize token mixing costs while preserving representation power. Training and inference recipes highlight straightforward integration into common vision tasks such as classification, detection, and segmentation. ... -
3
Mercury Agent
Soul-driven AI agent with permission-hardened tools, token budgets
Mercury Agent is a framework for building autonomous AI agents capable of executing complex workflows with minimal human intervention. It focuses on orchestrating tasks across multiple tools and services, enabling agents to perform end-to-end operations. The system includes mechanisms for planning, execution, and feedback, allowing agents to refine their actions iteratively. It supports integration with external APIs and services, making it adaptable to various domains. The architecture is... -
4
litelm
litellm without the bloat
...Async variants are available for the major operations. Provider errors are normalized into a shared exception hierarchy. The project intentionally omits load-balancing routers, caching, budgets, token counting, agents, image generation, and other heavier features. -
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.
-
5
MagiCrew
The first open-source all-in-one AI productivity platform
MagiCrew is an open source enterprise AI agent platform that combines assistants, expert agents, workflow automation, messaging, and collaborative productivity tools. It centralizes organizational data and knowledge so AI capabilities can be shared across teams. Administrators can set budgets by department, user, or task to control model spending. Sandboxed execution and human approval gates help contain risky automated actions. Agents can connect to internal systems such as ERP and CRM platforms and produce finished artifacts including reports, dashboards, presentations, and spreadsheets. Magic supports self-hosted Docker deployment as well as hosted and enterprise editions for organizations of different sizes. -
6
Bifrost
The Fastest LLM Gateway with built in OTel observability
Bifrost is an LLM gateway designed to provide a unified OpenAI-compatible API front for many different model providers. It abstracts away the complexity of working directly with multiple backend providers (OpenAI, Anthropic, AWS Bedrock, Google Vertex, etc.), enabling you to plug in providers and switch between them without touching your client code. It is built to be high performance: in benchmark tests at 5,000 requests per second, it reportedly adds only microseconds of overhead and... -
7
Fish Speech
SOTA Open Source TTS
Fish Speech is a state-of-the-art open-source text-to-speech project that has evolved into the OpenAudio series of advanced TTS models. The repository hosts the code and tooling for training, fine-tuning, and serving high-quality TTS, while the current flagship models (OpenAudio-S1 and S1-mini) are distributed via Fish Audio’s playground and Hugging Face. The models are evaluated with Seed TTS metrics and achieve exceptionally low word and character error rates, indicating strong... -
8
SimpleEnglish
Agent skill: make LLMs write docs in ASD-STE100
...It is designed for documentation, error messages, runbooks, incident reports, release notes, prompts, and translation preparation rather than marketing copy. The repository includes a complete skill, reusable system prompts, examples, evaluations, and a compact version for limited context budgets. It works with Agent Skills-compatible tools such as Claude Code, Cursor, Codex, Copilot, Gemini CLI, Goose, and OpenCode. Users without native skill support can paste the provided prompt into chatbot instructions or project configuration files. -
9
SlowFast
Video understanding codebase from FAIR for reproducing video models
SlowFast is a video understanding framework that captures both spatial semantics and temporal dynamics efficiently by processing video frames at two different temporal resolutions. The slow pathway encodes semantic context by sampling frames sparsely, while the fast pathway captures motion and fine temporal cues by operating on densely sampled frames with fewer channels. Together, these two pathways complement each other, allowing the network to model both appearance and motion without... -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
Sprix SAGE Router
State-aware SELF/COLLABORATE/HANDOFF routing for A2A agent 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. It learns contextual reliability and outcome information from previous execution evidence instead of relying on a single reputation score. Bounded search and replanning allow the router to compare feasible teams and revise decisions as task conditions change. -
11
LLM Course
Course to get into Large Language Models (LLMs)
...Learners get exposure to multiple adaptation strategies—LoRA/QLoRA, instruction fine-tuning, and alignment techniques—so they can choose approaches that fit their hardware and budgets. The materials also cover inference optimization and quantization to make serving LLMs feasible on commodity GPUs or even CPUs, which is crucial for side projects and startups. Evaluation is treated as a first-class topic, with examples of automatic and human-in-the-loop methods to catch regressions and verify quality beyond simple loss values. ... -
12
CogAgent
An open sourced end-to-end VLM-based GUI Agent
CogAgent is a 9B-parameter bilingual vision-language GUI agent model based on GLM-4V-9B, trained with staged data curation, optimization, and strategy upgrades to improve perception, action prediction, and generalization across tasks. It focuses on operating real user interfaces from screenshots plus text, and follows a strict input–output format that returns structured actions, grounded operations, and optional sensitivity annotations. The model is designed for agent-style execution rather... -
13
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
MiniMax-M1 is presented as the world’s first open-weight, large-scale hybrid-attention reasoning model, designed to push the frontier of long-context, tool-using, and deeply “thinking” language models. It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to... -
14
trimwise
Query-aware prompt compression for high-signal LLM prompts.
Trimwise is an extractive Python library for the step between collecting text and assembling a prompt. Give it a document, a maximum size, and optionally the task you care about. It selects useful fragments from across the document, returns them in source order, and guarantees that the measured result stays within your token, word, or character limit. This is especially useful when an agent has several sources but cannot place every source in the context window. Instead of taking the... -
15
Procgen
Procedurally-Generated Game-Like Gym-Environments
Procgen (short for Procedural Generation Benchmark) is a suite of 16 procedurally generated, game-like reinforcement learning environments designed to evaluate generalization and sample efficiency in RL agents. Unlike fixed, deterministic environments, Procgen generates new levels (layouts, obstacles, visual variation) each episode, making it impossible for an agent to simply memorize trajectories. The environments are designed to run very quickly (thousands of steps per second on a single... -
16
VaultGemma
VaultGemma: 1B DP-trained Gemma variant for private NLP tasks
...Training ran on TPU v6e using JAX and Pathways with privacy-preserving algorithms (DP-SGD, truncated Poisson subsampling) and DP scaling laws to balance compute and privacy budgets. Benchmarks on the 1B pre-trained checkpoint show expected utility trade-offs (e.g., HellaSwag 10-shot 39.09, BoolQ 0-shot 62.04, PIQA 0-shot 68.00), reflecting its privacy-first design.
- Previous
- You're on page 1
- Next
