Search Results for "context" - Page 15
Sort By:
Showing 1844 open source projects for "context"
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.
-
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.
-
1
Freebuff
The free coding agent
Freebuff is a suite of free AI tools for coding, application building, and research across desktop, terminal, browser, cloud, and chat interfaces. Its coding agents can inspect a project, locate relevant files, edit code, run commands, and review their own work. Specialized agents divide tasks such as context gathering, implementation, research, and validation. The desktop app can run multiple agents in isolated local workspaces. Web and cloud editions provide hosted sandboxes, previews, terminals, and deployment workflows. The platform also offers a curated model catalog and can connect locally installed coding agents in supported environments. -
2
usql
Universal command-line interface for SQL databases
...usql provides a simple way to work with SQL and NoSQL databases via a command-line inspired by PostgreSQL's psql. usql supports most of the core psql features, such as variables, backticks, and commands and has additional features that psql does not, such as syntax highlighting, context-based completion, and multiple database support. Database administrators and developers that would prefer to work with a tool like psql with non-PostgreSQL databases, will find usql intuitive, easy-to-use, and a great replacement for the command-line clients/tools for other databases. -
3
Halo
Framework built by White Circle for training large language
...The framework trains Hugging Face models directly, so checkpoints remain compatible with standard from_pretrained workflows. Distributed execution supports expert, context, tensor, and expert-tensor parallelism alongside FSDP2. Performance features include FlashAttention, DeepEP, Liger kernels, Grouped GEMM, BF16 optimizers, LoRA, and QLoRA. RL rollouts can run through vLLM or SGLang while overlapping with training. Halo also provides Docker images, YAML recipes, checkpoint tools, dataset utilities, benchmarks, and agent-oriented technical documentation. -
4
DSH Anchored Standard
Two-phase DeepSeek Harness preset
DSH Anchored Standard is a collection of experimental DeepSeek Harness presets designed to combine Minimal-style reasoning behavior with access to broader Standard tools. Its base mode begins a new session with only the real Minimal bash and text-editing tools while suppressing automatically injected context. After a durable tool call or assistant response, the preset promotes the session to a resident phase with discovery tools and restored Standard context. Additional modes experiment with zero-tool anchors, seeded trajectories, permanent Minimal catalogs, and separate thinking and execution stages. Promotion state is derived from persistent session events, so it survives reloads and resumed sessions. ... -
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.
-
5
Claude Codex Settings
My personal Claude Code and OpenAI Codex setup
...The project emphasizes practical usability, offering ready-to-use configurations that can be directly integrated into development environments. It also includes guidelines for structuring prompts, managing context, and optimizing interactions with AI systems. The repository serves as both a toolkit and a reference for improving developer productivity when working with AI assistants. It is particularly useful for users who want to standardize their workflows and reduce variability in results. Overall, Claude Codex Settings acts as a configuration layer that enhances the effectiveness of AI coding tools. -
6
LLM Wiki
Open Source Implementation of Karpathy's LLM Wiki
...It allows users to create interconnected knowledge bases that function similarly to a wiki but are enhanced with AI-driven content generation and summarization. The system emphasizes linking and context, enabling information to be connected across pages and topics for better navigation and understanding. It likely includes features for automatic content updates, ensuring that information remains relevant as new data becomes available. The architecture supports both manual editing and automated generation, providing flexibility in how knowledge is curated. ... -
7
RAG Web UI
RAG Web UI is an intelligent dialogue system based on RAG
RAG Web UI is an open-source intelligent dialogue system built on retrieval-augmented generation technology, designed to enable users to create AI-powered question answering systems grounded in their own knowledge bases. It combines document retrieval with large language models to provide accurate, context-aware responses based on indexed data rather than generic model knowledge. The platform supports ingestion of multiple document formats, including PDFs, Word files, Markdown, and plain text, automatically processing and vectorizing them for efficient retrieval. It features a multi-turn conversational interface that maintains context across interactions, allowing users to engage in more natural and continuous dialogues with their data. ... -
8
kubectl-ai
AI assistant for managing Kubernetes clusters from the terminal
kubectl-ai is an AI-powered command-line assistant designed to help users manage and interact with Kubernetes clusters through natural language queries. It acts as an intelligent interface that interprets user intent and translates it into appropriate Kubernetes operations and commands. By integrating large language models, it enables users to ask questions or request actions in plain language instead of manually crafting complex Kubernetes commands. kubectl-ai runs directly in the terminal... -
9
Qwen3-ASR
Qwen3-ASR is an open-source series of ASR models
...As a specialized ASR variant of the broader Qwen language model ecosystem, it focuses on capturing reliable transcriptions from audio sources such as recordings, live streams, or conversational inputs while supporting low latency use cases. The architecture combines advanced neural acoustic modeling with context-aware language prediction so that outputs maintain both fidelity to the original speech and grammatical coherence. This makes Qwen3-ASR suitable for voice-driven applications like AI assistants, dictation tools, speech analytics pipelines, and accessibility features, where accurate and fluid transcription is critical. -
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.
-
10
Lingui.js
A readable, automated, and optimized (3 kb) internationalization
...Use React components inside localized messages without any limitations. Writing rich-text messages is as easy as writing JSX. For AI to do great translations for you, context is critical. Translating UI copy is difficult because it's usually a list of short strings without enough context. Lingui's localization formats allow developers to write descriptions of where and how your keys are used. -
11
dsh-TUI
DSH official WeChat featured TUI plugin
dsh-TUI is a full-screen terminal interface for DeepSeek Harness inspired by the interaction style of Claude Code. It streams Markdown, tool calls, reasoning status, token usage, context consumption, and throughput directly in the terminal. Users can resume, fork, compact, search, rewind, and switch models while preserving session history through DSH services. File references, image attachments, slash commands, questionnaires, and keyboard-driven input are built into the interface. Long conversations use event-driven rendering, virtualization, and bounded caches to control terminal and memory costs. ... -
12
deepsec
Deepsec is a security harness for finding vulnerabilities
...It is designed to run on the user’s own infrastructure, using coding agents to perform deep, project-aware security review rather than only basic pattern matching. The tool initializes a project-specific security context, scans code in batches, processes findings, and can optionally revalidate results to reduce false positives. For large repositories, it supports parallel work across worker machines and can resume interrupted scans without repeating completed work. It is aimed at serious security reviews where deeper model reasoning may be worth the higher compute and model cost. ... -
13
claude-obsidian
Claude + Obsidian knowledge companion
...It includes features such as contradiction detection, orphaned note identification, and automatic indexing. A persistent memory layer ensures continuity across sessions, eliminating the need for repeated context. It also performs autonomous research to fill knowledge gaps and expand the knowledge base. Overall, it turns note-taking into an active, compounding intelligence system. -
14
Witr
witr exists to answer "Why is this running?"
...It supports major operating systems including Linux, macOS, Windows, and FreeBSD, and produces human-readable output that succinctly shows the causal ancestry of a process (e.g., systemd → pm2 → node). witr aims to reduce the time it takes to diagnose processes, especially during debugging or outage investigations, by providing context that would otherwise require manual analysis across multiple tools. -
15
OpenDeepResearcher
AI researcher that continuously searches for information
OpenDeepResearcher is a notebook-based AI research agent that searches the web iteratively until it has enough context to produce a final report. A user provides a research topic, and the system generates search queries with an LLM. It then runs concurrent searches, deduplicates links, fetches page content, evaluates whether each page is useful, and extracts relevant context. After each round, the model decides whether more searches are needed or whether the available evidence is enough. ... -
16
Solana Agent Kit
Connect any ai agents to solana protocols
solana-agent-kit is an open-source toolkit that enables AI agents to connect with Solana blockchain protocols. It allows any AI agent, regardless of the underlying model, to autonomously perform over 60 Solana actions, including token trading, launching new tokens, lending assets, sending compressed airdrops, executing blinks, launching tokens on Automated Market Makers (AMMs), and bridging tokens across chains. -
17
CTeX-kit
Macro Packages and Scripts for Chinese TeX users
CTeX-kit is a collection of TeX/LaTeX/ConTeXt macro packages, related scripts, and resource files made specifically for Chinese TeX users, especially Mandarin users. This project aims to bring together many existing efforts including ctex, xeCJK, zhspacing, LuaTeX-related Chinese support, etc. -
18
Codex plugin for Claude Code
Use Codex from Claude Code to review code or delegate tasks
...The system emphasizes interoperability, allowing developers to plug Codex capabilities into broader agent ecosystems without rewriting core logic. It may also include mechanisms for managing execution context, permissions, and tool access, ensuring that generated code can be safely applied. This makes it particularly useful for complex development pipelines where multiple agents or tools need to collaborate. -
19
verl-agent
Designed for training LLM/VLM agents via RL
...The framework supports multi-turn interactions between agents and their environments, allowing the system to receive feedback after each step and adjust its strategy accordingly. This step-wise interaction model makes it possible to train agents to operate in long-horizon scenarios where decisions depend on cumulative context and previous outcomes. Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
20
Chat UI
The open source codebase powering HuggingChat
...Chat UI connects to any service that exposes an OpenAI-compatible API endpoint, allowing it to work with a wide range of models and inference providers. The platform supports advanced capabilities such as multimodal input, tool integration through Model Context Protocol servers, and intelligent routing that selects the most appropriate model for each request. -
21
Step 3.5 Flash
Fast, Sharp & Reliable Agentic Intelligence
...Unlike dense models that activate all their parameters for every token, Step 3.5 Flash uses a sparse Mixture-of-Experts (MoE) architecture that selectively engages only about 11 billion of its roughly 196 billion total parameters per token, delivering high-quality reasoning and interaction at far lower compute cost and latency than traditional large models. Its design targets deep reasoning, long-context handling, coding, and real-time responsiveness, making it suitable for building autonomous agents, advanced assistants, and long-chain cognitive workflows without sacrificing performance. -
22
ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | Open Source Bilingual Chat
...It keeps the series’ smooth dialog and low deployment cost while adding native tool use (function calling), a built-in code interpreter, and agent-style workflows. The family includes base and long-context variants (8K/32K/128K). The repo ships Python APIs, CLI and web demos (Gradio/Streamlit), an OpenAI-format API server, and a compact fine-tuning kit. Quantization (4/8-bit), CPU/MPS support, and accelerator backends (TensorRT-LLM, OpenVINO, chatglm.cpp) enable lightweight local or edge deployment. -
23
TraceRoot
Find the Root Cause in Your Code's Trace
...Human-in-the-loop interaction is central: developers can guide reasoning by selecting relevant spans or logs, then verify agent reasoning through traceable context. -
24
OpenAI
Swift community driven package for OpenAI public API
...The SDK supports a wide range of features including chat completions, embeddings, image generation, audio processing, and structured outputs, making it a comprehensive toolkit for building AI-powered applications. It also includes support for advanced features such as function calling, assistants, and tool integration through protocols like Model Context Protocol, enabling more complex and interactive AI workflows. -
25
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
...Its architecture supports a very large context window (on the order of 128K tokens during training), which lets it handle complex multimodal inputs like long documents, multi-page reports, or video transcripts, while maintaining coherence across extended content. In benchmarks and internal evaluations, GLM-4.6V achieves state-of-the-art (SoTA) performance among models of comparable parameter scale on multimodal reasoning.
