Search Results for "context" - Page 11
Sort By:
Showing 459 open source projects for "context"
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.
-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
1
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
KVCache-Factory is an open-source research framework designed to explore and implement unified key-value cache compression techniques for autoregressive transformer models. In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression... -
2
Eigent
The Open Source Cowork Desktop to Unlock Your Exceptional Productivity
...You can run Eigent fully locally for maximum privacy and data control, or choose a cloud-connected experience for quick access. The platform supports a wide range of AI models and integrates powerful tools through the Model Context Protocol (MCP). With human-in-the-loop controls and enterprise-ready features, Eigent balances automation with oversight and security. -
3
LangExtract
A Python library for extracting structured information
...It is designed to transform free-form text into reliable, schema-constrained data while maintaining traceability back to the source material. Each extracted entity is precisely grounded in its original context, allowing visual inspection and validation via automatically generated interactive HTML visualizations. LangExtract supports a wide range of models, including Google Gemini, OpenAI GPT, and local LLMs via Ollama, making it adaptable to different deployment environments and compliance needs. The system excels at handling long documents using optimized chunking, multi-pass extraction, and parallel processing to ensure both high recall and structured consistency. -
4
Mem0
The Memory layer for AI Agents
...Key features include enhancing future conversations by building smarter AI that learns from every interaction, reducing LLM costs by up to 80% through intelligent data filtering, delivering more accurate and personalized AI outputs by leveraging historical context, and offering easy integration compatible with platforms like OpenAI and Claude. Mem0 is perfect for projects such as customer support, where chatbots remember past interactions to reduce repetition and speed up resolution times; personal AI companions that recall preferences and past conversations for more meaningful interactions; AI agents that learn from each interaction to become more personalized and effective over time. -
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.
-
5
Checkov
Prevent cloud misconfigurations during build-time for Terraform
...Scan cloud resources in build-time for misconfigured attributes with a simple Python policy-as-code framework. Analyze relationships between cloud resources using Checkov’s graph-based YAML policies. Execute, test, and modify runner parameters in the context of a subject repository CI/CD and version control integrations. -
6
Vibe Coding CN
The ultimate workstation for turning ideas into reality
...It presents a workflow for turning ideas into working projects through structured AI pair programming. The methodology emphasizes planning, modular architecture, clear goals, strong context, and human review instead of uncontrolled AI generation. It covers project conception, technology selection, implementation, debugging, testing, and expansion. The repository also organizes prompts, reusable skills, project templates, tool recommendations, and configuration guidance. Its broader goal is to make AI coding workflows more systematic, maintainable, and reusable across development projects. -
7
Deep Agents
The batteries-included agent harness
Deep Agents is an open-source, batteries-included agent harness designed for long-running, multi-step AI work. It provides an opinionated agent setup while allowing developers to override or replace individual pieces without forking the project. The framework is model-agnostic and works with tool-calling models from hosted providers, open-weight deployments, or local runtimes. Built on LangGraph, it includes persistence, checkpointing, streaming, and production-oriented orchestration. Agents... -
8
MCP Agent Mail
Asynchronous coordination layer for AI coding agents
...It gives each agent a persistent identity, inbox, outbox, searchable history, and threaded Markdown conversations. Agents can send decisions, status updates, images, and attachments without relying on a human to relay context between parallel sessions. Advisory file reservations let an agent declare intended edits to files or patterns, reducing accidental overlap without enforcing rigid locks. Git stores human-auditable communication artifacts, while SQLite supports indexing, search, and operational queries. The HTTP-only FastMCP server works with clients such as Claude Code, Codex, Gemini CLI, and other MCP-compatible tools. ... -
9
code-review-graph
Local-first code intelligence graph for MCP and CLI
...It parses source files with Tree-sitter and stores functions, classes, imports, calls, inheritance, and test relationships in a SQLite graph. When code changes, blast-radius analysis identifies the callers, dependents, and tests most likely to be affected. AI coding assistants can query this focused context through MCP instead of repeatedly scanning an entire codebase. Incremental indexing reparses only changed files and their relevant dependencies, making it practical for large repositories and monorepos. The command-line installer can detect and configure numerous supported coding tools automatically. It also offers watch mode, hooks, skills, a VS Code extension, and review-oriented risk analysis. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
Timbal
Simple, performant, battle-tested framework for building reliable AI
...The framework supports multiple model providers and can automatically fail over between configured models. Human approval gates can pause runs, preserve their state, and resume them after a process restart. Built-in capabilities cover persistent memory, context compaction, structured outputs, reusable skills, MCP servers, tracing, and evaluations. Applications can run locally, be self-hosted, or be deployed through the Timbal platform with an accompanying API and user interface. -
11
TabFM
scikit-learn compatible tabular foundation model
...It is designed to work with mixed numerical and categorical columns without requiring a custom training run for every new table. Instead of fitting model weights to the user’s dataset, TabFM uses in-context learning by reading training examples and test rows together at inference time. The library provides scikit-learn-compatible classifier and regressor interfaces, which makes it familiar for data scientists already using Python ML workflows. It supports both JAX and PyTorch backends and can automatically download pretrained TabFM v1.0.0 weights. ... -
12
ComfyUI-HunyuanVideoWrapper
ComfyUI wrapper nodes for HunyuanVideo
...The system introduces specialized nodes such as text-image encoders that allow multiple image inputs to be referenced directly within prompts. This makes it possible to guide generation using both visual and textual context simultaneously. The wrapper is designed to fit seamlessly into ComfyUI pipelines, enabling chaining with other nodes for advanced workflows. It supports prompt-based referencing of images, where placeholders in text correspond to connected inputs, allowing fine control over generation behavior. The project is particularly useful for creators experimenting with multimodal AI video synthesis. -
13
colleague-skill
Transform a cold separation into a warm Skill
colleague-skill is a specialized agent skill designed to simulate a collaborative teammate within AI-driven workflows, enabling agents to behave more like human colleagues in problem-solving scenarios. The project focuses on enhancing interaction quality by introducing role-based behavior, contextual awareness, and cooperative task execution. It allows agents to provide suggestions, feedback, and alternative approaches, mimicking real-world collaboration dynamics. The system likely... -
14
VideoRAG
"VideoRAG: Chat with Your Videos
...This approach allows it to handle videos of arbitrary length without requiring the entire content to be passed into the model at once, overcoming token limits and enabling detailed, context-aware interaction. -
15
MCPM.sh
CLI MCP package manager & registry for all platforms and all clients
mcpm.sh is an open-source command-line package manager and registry designed for managing Model Context Protocol (MCP) servers across various clients and platforms. It facilitates the installation, configuration, and orchestration of MCP servers, enabling users to group servers into profiles and route requests through a unified interface. With its advanced router and profile features, mcpm.sh simplifies the management of complex MCP environments, supporting clients like Claude Desktop, Cursor, and Windsurf. ... -
16
Ibis
Expressive analytics in Python at any scale
...To select a subset of a table's columns, or to add new columns, you must produce a new table by means of a projection. If you pass a function instead of a string or Ibis expression in any projection context, it will be invoked with the "parent" table as its argument. This can help significantly when [composing complex operations. -
17
IceCream
Never use print() to debug again
Do you ever use print() or log() to debug your code? Of course you do. IceCream, or ic for short, makes print debugging a little sweeter. With arguments, ic() inspects itself and prints both its own arguments and the values of those arguments. Just give ic() a variable or expression and you're done. ic() returns its argument(s), so ic() can easily be inserted into pre-existing code. Additionally, ic()'s output can be entirely disabled, and later re-enabled, with ic.disable() and ic.enable()... -
18
files-to-prompt
Concatenate a directory full of files into a single prompt
files-to-prompt is a Python command-line tool that takes one or more files or entire directories and concatenates their contents into a single, LLM-friendly prompt. It walks the directory tree, outputting each file preceded by its relative path and a separator, so a model can understand which content came from where. The tool is aimed at workflows where you want to ask an LLM questions about a whole codebase, documentation set, or notes folder without manually copying files together. It... -
19
geo-seo-claude
GEO-first SEO skill for Claude Code
...It leverages AI to generate location-specific content tailored to different regions, allowing users to scale SEO efforts across multiple cities or markets without manual content creation. The system focuses on producing structured and keyword-optimized pages that align with search engine ranking factors, including localized relevance and semantic context. It is particularly useful for agencies, marketers, and businesses that need to manage large volumes of localized landing pages efficiently. Geo SEO Claude can integrate with existing content pipelines, enabling automated generation and deployment of SEO assets. It also supports customization of content templates, allowing users to maintain brand consistency while scaling output. -
20
IQuest-Coder-V1 Model Family
New family of code large language models (LLMs)
...These models range from tens of billions to smaller footprints and are trained on a novel code-flow multi-stage paradigm that captures how real software evolves over time — not just static code snapshots — giving them a deeper semantic understanding of programming logic. They support native long contexts up to 128K tokens, enabling them to reason across large codebases and multi-file interactions without context fragmentation, and include “Thinking” variants optimized for complex reasoning and “Loop” variants with recurrent mechanisms to improve inference efficiency. IQuest-Coder-V1 delivers state-of-the-art performance on multiple coding benchmarks, demonstrating strong results in competitive programming, tool use, and agentic code generation. -
21
Rasa
Open source machine learning framework to automate text conversations
...Rasa helps you build contextual assistants capable of having layered conversations with lots of back-and-forths. In order for a human to have a meaningful exchange with a contextual assistant, the assistant needs to be able to use context to build on things that were previously discussed. Rasa enables you to build assistants that can do this in a scalable way. Rasa uses Poetry for packaging and dependency management. If you want to build it from the source, you have to install Poetry first. By default, Poetry will try to use the currently activated Python version to create the virtual environment for the current project automatically. -
22
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. -
23
GPTImage2Skill
GPT Image 2 prompt gallery, image prompt library, agentic skill
...The project is designed to help agents and users produce stronger visual outputs without starting from a blank prompt every time. Its gallery is organized into category files so an agent can load only the relevant prompt references instead of overwhelming the context window. It also includes installation paths for skill-capable environments such as Claude Code, Codex, OpenClaw, and other agent runtimes. Overall, it is useful as both a learning resource for prompt structure and a practical toolkit for repeatable image generation workflows. -
24
memsearch
A Markdown-first memory system, a standalone library for any AI agent
memsearch is a markdown-first memory system designed to provide long-term memory capabilities for AI agents through structured storage and semantic retrieval. It enables agents to store, organize, and retrieve information using embeddings and hybrid search techniques, ensuring that relevant context is always available. The system supports advanced features such as reranking and progressive disclosure, which help prioritize the most useful information for a given query. It integrates with vector databases like Milvus, enabling scalable storage and retrieval of large datasets. Memsearch is designed to be agent-friendly, making it easy to plug into existing AI workflows and enhance reasoning capabilities. ... -
25
ShellOracle
A terminal utility for intelligent shell command generation
ShellOracle is a command-line utility designed to translate natural language instructions into executable shell commands, enhancing productivity for developers and system administrators. It integrates with multiple large language model providers, including local and cloud-based systems, to generate accurate and context-aware command suggestions. The tool operates directly within the terminal and can be triggered through keyboard shortcuts, allowing users to describe tasks in plain English and receive ready-to-run commands. It maintains a history of prompts and generated commands, enabling users to revisit previous queries and refine workflows over time. ...
