| 10/14 | 9 |
LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.
|
| 10/14 | 9 |
DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.
|
| 10/13 | 9 |
Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.
|
| 10/12 | 9 |
Full-stack application for turning documents into context for LLMs with multi-user management.
|
| 10/12 | 9 |
Tool for building integrated AI assistants and agents that operate within user applications.
|
| 10/12 | 9 |
Self-hosted developer control center that runs coding agents across local, remote, or cloud backends and automates everyday engineering workflows.
|
| 10/11 | 9 |
MCP-based server that provides LLMs real-time, unblocked access to live web data and browser automation.
|
| 10/08 | 9 |
Compact, human-readable serialization format optimized for structured data in large language model inputs with reduced token usage.
|
| 10/14 | 8 |
Desktop widget that monitors live token usage and AI tool limits across multiple AI coding tools with real-time multi-device sync and usage history breakdowns.
|
| 10/13 | 8 |
High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.
|
| 10/13 | 8 |
Model Context Protocol server that optimizes Claude Code context usage using caching, Brotli compression, and smart tool replacements for large text and file operations.
|
| 10/13 | 8 |
Finds relevant files in a codebase and supplies compact function and class signatures to AI models to reduce tokens and improve answers.
|
| 10/12 | 8 |
API gateway that routes and manages requests across multiple LLM providers with an OpenAI-compatible API, usage analytics, and cost tracking.
|
| 10/12 | 8 |
AI-powered browser extension for immersive language learning with translation and article analysis.
|
| 10/11 | 8 |
Biologically inspired memory layer for AI agents with decay, consolidation, and cross-tool portability.
|
| 10/11 | 8 |
End-to-end streaming framework for building multi-modal agents with typed signatures.
|
| 10/09 | 8 |
Fetches up-to-date documentation and code examples for prompts in LLMs.
|
| 10/09 | 8 |
Knowledge-based platform leveraging LLMs for data processing, retrieval, and AI workflow orchestration.
|
| 10/08 | 8 |
Framework for building agents and LLM-powered applications with modular components and integrations.
|
| 10/08 | 8 |
A Ruby library providing a unified API for interacting with various AI models and services.
|
| 10/14 | 7 |
Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.
|
| 10/14 | 7 |
Generative Business Intelligence agent that allows teams to interact with data for generating insights, reports, and visualizations.
|
| 10/14 | 7 |
Pure-Go, single-file embedded AI memory and knowledge graph library that provides hybrid vector and lexical retrieval, RDF/SPARQL graph features, and MCP tools via SQLite.
|
| 10/14 | 7 |
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.
|
| 10/14 | 7 |
Opinionated TypeScript framework for building AI applications and features quickly.
|
| 10/13 | 7 |
Tool for running and managing large language models.
|
| 10/13 | 7 |
Containerized toolkit to run local LLM backends, frontends, and related services with minimal configuration.
|
| 10/13 | 7 |
Cloud-native, multi-database platform for automated provisioning, deployment, scaling, and management on Kubernetes.
|
| 10/13 | 7 |
Zero-dependency TypeScript runtime for production AI agents, providing durable execution, persistent memory, tool calling, approvals, and resumable runs across Node, Bun, Deno, and edge.
|
| 10/13 | 7 |
Desktop application providing live speech translation and audio routing using multiple AI-powered APIs.
|
| 10/12 | 7 |
Local-first desktop workspace that runs personal AI agents in rooms with chained leadership, local memory, file-based skills, and human-gated actions.
|
| 10/12 | 7 |
Local knowledge engine for notes, code, PDFs, and Office docs with hybrid search, citations, and verified, explainable answers via CLI, Web UI, REST API, SDK, and MCP.
|
| 10/12 | 7 |
OC Ferry forwards OpenAI-compatible requests to OpenCode free models via WorkBuddy, with concurrency checks and caching across an isolated runtime.
|
| 10/12 | 7 |
Live arena where LLM trading agents trade real market data with virtual money while exposing every thought, tool call, and post-trade review.
|
| 10/11 | 7 |
Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.
|
| 10/10 | 7 |
Coddy is a distroless-friendly Go-based general-purpose agent harness with a ReAct loop, ACP/HTTP/Telegram interfaces, MCP and skills integration, and long-term memory.
|
| 10/10 | 7 |
Mock infrastructure for testing AI applications' external services like LLMs, multimedia APIs, agent protocols, and vector databases.
|
| 10/10 | 7 |
Novel-analysis visualization tool producing character relationship graphs, maps, timelines and encyclopedias with local and cloud LLM support.
|
| 10/09 | 7 |
TypeScript-native multi-agent orchestration that decomposes goals into parallel task DAGs and synthesizes results.
|
| 10/09 | 7 |
AI app that converts stories and scripts into animated short dramas with scriptwriting, storyboarding, and character/video generation.
|
| 10/09 | 7 |
Rails engine providing an agent DSL, execution tracking, cost analytics, reliability controls, and a real-time dashboard for LLM-powered agents.
|
| 10/09 | 7 |
TencentDB Agent Memory provides symbolic short-term and layered long-term memory for AI agents to retain context and reduce token usage without external APIs.
|
| 10/09 | 7 |
Tool for enhancing prompt quality to improve AI interaction results.
|
| 10/09 | 7 |
Professional MCP server for PostgreSQL database operations, monitoring, and performance analysis with version-adaptive features.
|
| 10/08 | 7 |
TypeScript framework for building and orchestrating AI workflows and agent-driven development with integrated prompts, tracing, evals, and secrets management.
|
| 10/14 | 6 |
Highly configurable AI virtual executive persona with eight specialist agents, RAG from knowledge and company documents, episodic memory, and workflow scheduling across common chat and email tools.
|
| 10/14 | 6 |
Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.
|
| 10/14 | 6 |
Local-first AI workspace providing multi-agent chat, coding, and visual workflow automation across desktop and self-hosted web.
|
| 10/13 | 6 |
Auto-tuned launcher that measures multi-GPU hardware for GGUF models, picks an optimal llama.cpp/ik_llama.cpp backend, and serves an OpenAI-compatible API.
|
| 10/13 | 6 |
OpenAI-compatible privacy proxy that masks personal data and secrets before they reach external LLMs.
|
| 10/12 | 6 |
Local-first A 股行情分析与AI智能投研代理，支持日常共识与短线研判。
|
| 10/12 | 6 |
Production-ready, self-hosted multi-model AI workspace with interleaved tool execution, RAG knowledge bases, persistent Python sandbox, team workspaces, and full admin backend.
|
| 10/12 | 6 |
Universal intelligence layer that orchestrates LLMs, tools, and data to build stateful, multimodal agentic applications.
|
| 10/12 | 6 |
Local-first AI office agent that generates and edits PPT, Word, and Excel files by using pluggable LLM backends without storing chat logs.
|
| 10/11 | 6 |
NestJS module that exposes tools, resources, and prompts using the Model Context Protocol.
|
| 10/11 | 6 |
Privacy-first self-hosted chat interface connecting to local and cloud AI providers with a plugin system and no telemetry or tracking.
|
| 10/11 | 6 |
High-performance in-browser LLM inference engine using WebGPU for hardware-accelerated, serverless model inference.
|
| 10/11 | 6 |
Browser-native 3D AI agent platform that turns prompts or GLB inputs into textured models with LLM brains and on-chain registration.
|
| 10/10 | 6 |
Single-page web interface for chatting with local Ollama models directly from the browser, with streaming responses, attachments, and local chat history.
|
| 10/09 | 6 |
Autonomous company OS where Linux-sandboxed AI agents run code, manage files, and automate operations 24/7.
|
| 10/09 | 6 |
Platform to host, deploy, build, and fine-tune large language models with OpenAI API compatibility.
|
| 10/09 | 6 |
Cross-platform Markdown note-taking application using AI to organize fragmented knowledge into readable notes.
|
| 10/09 | 6 |
Desktop AI agent workspace that connects models with tools and personal knowledge to produce and manage real deliverable artifacts.
|
| 10/09 | 6 |
Inference engine for running LLMs locally and efficiently on any device.
|
| 10/09 | 6 |
Pixeltable Cloud provides a unified multimodal backend for AI data apps, combining database, orchestration, and serving in a single Python file.
|
| 10/09 | 6 |
AI coding workspace with parallel Git worktrees, split terminals for multiple agents, and checkpoint-based diff restore with Blueprint and Island workflows.
|
| 10/08 | 6 |
Developer-friendly local tool for testing, evaluating, and securing large language model applications.
|
| 10/07 | 6 |
Visual platform for building and deploying AI workflows, agents, and multimodal pipelines via drag-and-drop nodes.
|
| 10/14 | 5 |
JavaScript/TypeScript SDK for using local LLMs.
|
| 10/14 | 5 |
OneBot v11 bridge that turns a spare QQ account into an AI group member, paired with a zero-build web console to manage prompts, persona, and memory.
|
| 10/13 | 5 |
Monorepo managing multiple npm packages under the @elevenlabs scope.
|
| 10/13 | 5 |
Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.
|
| 10/13 | 5 |
A personal writing agent that organizes notes, self-checks settings, and tracks plot foreshadowing without writing for you.
|
| 10/13 | 5 |
Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.
|
| 10/13 | 5 |
AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.
|
| 10/13 | 5 |
Linux QQ group chat agent for OneBot v11 with segmented messages, sticker support, proactive sending, and built-in operations commands.
|
| 10/12 | 5 |
Desktop and terminal menu-bar app that lets you view and switch each installed AI agent’s configured model via a local model gateway.
|
| 10/12 | 5 |
Private GenAI stack for deploying AI agents with support for RAG, API calls, vision, and efficient GPU scheduling.
|
| 10/12 | 5 |
Text-to-SQL access control that prunes database schemas by caller grants so restricted tables never enter the LLM prompt for agents across popular SQL databases.
|
| 10/11 | 5 |
Self-hosted retrieval-augmented generation engine that keeps all document processing and answering offline on a single binary, with cited sources.
|
| 10/11 | 5 |
Agentic OS that provides a guardrailed environment for collaborative human and agent workflows with persistent tools, memory, and interfaces.
|
| 10/11 | 5 |
Cross-platform AI voice typing app that transcribes speech, rewrites it with LLMs, and sends polished text back into the active application.
|
| 10/11 | 5 |
Casbin Gateway provides an endpoint that tracks AI coding agents’ requests and grades whether the accessed model API matches the paid provider, with per-agent permissions and records.
|
| 10/11 | 5 |
WeChat iLink-based agent bot that receives inbox events via webhook or pull and sends messages or media through an HTTP API.
|
| 10/11 | 5 |
Local speech transcription and AI answering for live meetings and interviews, with on-screen responses, suggested questions, screen analysis, and end-of-call meeting reports.
|
| 10/10 | 5 |
Organization layer for running your own organization of agents.
|
| 10/10 | 5 |
Go SDK providing a unified API for 25+ AI providers with streaming, structured output, and MCP support.
|
| 10/09 | 5 |
TypeScript toolkit for building AI-powered applications with popular frameworks.
|
| 10/09 | 5 |
Terminal-native unified runtime for specialized AI agents built on pluggable LLMs, search backends, personas, and skills.
|
| 10/09 | 5 |
Default UI for DIAL offering conversation interface, IDP support, model side-by-side comparison, extensions and theming.
|
| 10/09 | 5 |
On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.
|
| 10/08 | 5 |
Desktop companion app with local-first memory, expressive Live2D/VRM avatars, and voice chat driven by an installed ACP agent.
|
| 10/14 | 4 |
High-performance desktop LLM proxy that unifies access to many models and providers via a single OpenAI-compatible API.
|
| 10/14 | 4 |
Durable content ingestion and hybrid search engine for monitoring topics over time, with plugin-based connectors, enrichments, and business rules.
|
| 10/13 | 4 |
Local, private, self-improving content discovery agent that learns from interactions to find videos and posts across Bilibili, Xiaohongshu, Douyin, YouTube, and more.
|
| 10/12 | 4 |
Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.
|
| 10/11 | 4 |
Opinionated TypeScript monorepo fork of pi-mono that provides a curated coding-agent runtime with builtin extensions and core tweaks.
|
| 10/11 | 4 |
Passively evolving enterprise world model that captures knowledge, rules, reasoning, and controlled execution over time.
|
| 10/13 | 3 |
AI desktop notebook that answers using your own documents with verified page citations, and lets you write drafts and take meeting notes on macOS, Windows, and Linux.
|
| 10/13 | 3 |
Desktop notebook app for macOS, Windows, and Linux that answers questions from your own documents while verifying quoted citations and helping you write with AI models.
|
| 10/08 | 2 |
State-machine-powered LLM agent logic built on XState, where model decisions and tool effects run within explicit, inspectable control flow.
|