Self Hosted Llm Chat Api

LLMChat is an AI chat tool that offers a beta version experience with diverse AI models, personalized memory, custom assistant creation, and privacy-focused locally stored conversations. Explore features like plugin integration, tailored preferences, and prompt examples for various tasks.

Open‑Chat is a self‑hostable, decentralized chat platform that supports both proprietary and open‑source AI models. It provides a full chat API, runs LLMs on local GPUs, lowers latency, enhances privacy, and deploys easily on personal or cloud servers.

LM Studio runs open‑source large language models locally on Mac (M‑series), Windows, and Linux, enabling private, offline inference. It offers command‑line and headless deployment, server‑side API, SDKs, a model hub, and LM Link for remote model access.

Llamachat is an AI tool enabling chat with llama, alpaca, and GPT-4 models on Mac. It offers a chatbot-like experience, supports model conversion, and is open-source for contributions on GitHub.

LiteLLM is an open‑source gateway that unifies access to 100+ LLMs through a single OpenAI‑compatible API, enabling provider fallback, cost tracking, tag‑based budgeting, guardrails, observability, and on‑prem or cloud deployment with a lightweight SDK.

LLMAPI is a unified OpenAI-compatible LLM gateway offering access to 100+ models across providers, centralized API key management, failover routing, performance and cost analytics, and team-oriented key controls to simplify integration and operations.

LLMStack is an open‑source platform that lets developers build AI agents and workflows without coding, supports multiple model providers, imports data from web, PDFs, audio, cloud services, and offers a collaborative React UI with granular permissions.

Duck.ai offers anonymous access to popular AI models. It ensures privacy by keeping conversations untracked and outside AI training data, with seamless model switching.

LiveKit is an open-source framework and cloud platform for building and hosting low-latency real-time voice, video and physical AI agents, offering a media server, WebRTC SDKs, TTS/STT and telephony connectors, scalable hosting and programmatic APIs.

Llama is a local AI tool that enables users to create customizable and efficient language models without relying on cloud-based platforms, available for download on MacOS, Windows, and Linux.

Omnichat is a multimodal LLM API that enables autonomous applications by integrating various AI capabilities. It enhances automation, customer service, and workflow management with human-like reasoning for better context comprehension and decision-making.

Atomic Chat is a fully offline, on-device AI chat app for macOS, Windows, Linux, iOS, and Android that runs 1,000+ LLMs locally with built-in agent support, persistent memory, and privacy-first design. It features TurboQuant optimizations for up to 8x faster attention and lower memory use, with one-

CoPaw is an open-source, modular AI agent workstation (Agentscope) for local or cloud deployment, unifying model layers, plugins and long-term memory. It supports local LLMs, multi-channel chat, schedulers and CLI tools for custom agents and workflows.

Uncensored AI delivers a chat platform featuring Claude Opus, Gemini, Grok, and MiniMax M2‑Her. It supports text, audio, image, and code interactions, including image‑to‑video via Image Studio. API beta and usage stats benefit developers, writers, educators, and researchers.

Helploom combines live chat, a shared inbox and an AI chatbot trained on your knowledge base to automate 24/7 multilingual support, searchable help center, analytics, escalation to human agents, and developer integration via a JS widget and REST API.

Chainlit is an open-source framework for building conversational AI applications that supports multimodal interactions, integrates with authentication providers, offers a prompt playground for optimization, and ensures data privacy through a self-hosted platform for managing conversational data.

Sapling offers a language‑model API that delivers real‑time grammar corrections in enterprise workspaces and messaging platforms. Developers embed it into editors, CRMs, and customer‑service tools with a simple SDK/API, while the platform supports private cloud, encryption, PII redaction, SSO, and s

Open‑source AI code‑review platform that plugs into GitHub, GitLab, Bitbucket, and Azure DevOps at the pull‑request level. Model‑agnostic, it runs custom rule sets, tracks technical debt, and delivers real‑time metrics without storing source code.

Awan LLM offers unlimited token generation with Meta Llama 3.1 8B and 70B models, no censorship or caps, supporting persistent AI assistance, autonomous agents, roleplay, data processing, and code completion, hosted on owned GPUs for continuous use.

LiveChatAI uses GPT‑4o to transform a knowledge base into a chatbot that auto‑resolves ~70 % of tickets. It imports content from sites, PDFs, Notion, YouTube, Q&A, supports 95 languages, automates booking, payments, CRM updates, and integrates with WhatsApp, Shopify, WordPress, Slack.

Chatclient lets businesses build ChatGPT‑based chatbots trained on uploaded content. It supports 95+ languages, auto‑retraining, custom personas, and white‑label deployment, and integrates with Slack, WhatsApp, Zapier, APIs, and web/mobile apps.

Mtalkz is a cloud communication platform offering bulk SMS, RCS, WhatsApp API, OTP, IVR, email, and chatbot services. It supplies APIs, real‑time analytics, regulatory compliance support, and scalable messaging for businesses of all sizes.

Voiceflow enables teams to create, test, and deploy AI‑powered conversational agents across chat, voice, phone, and web without coding. Its visual editor, real‑time collaboration, and secure deployment pipelines streamline design, evaluation, and omnichannel rollout.

Chatworm offers web, Android, and Windows interfaces to chat with multiple LLMs (OpenAI, Anthropic, DeepSeek, Gemini, Qwen, Mistral, Grok). It supports Whisper speech, TTS voices, DALL‑E 3 image creation, ChatGPT Vision analysis, model switching, and dark mode. Open‑source on GitHub.

Z.ai chat is an AI-driven conversational tool that utilizes advanced natural language processing to facilitate interactive dialogue and deep search for applications in tech blogs, coding, and research, with API support for developers and content organization features.

Secret Llama is a private browser-based chatbot that stores data locally, ensuring enhanced privacy. It supports offline use after initial model download and functions on Chrome and Edge with GPU support, encouraging community contributions for ongoing improvements.

LemonChat is an anonymous chat platform that connects users with strangers via text and video. It features interest-based matching, gender preference filters, and continuous moderation, ensuring a safe and engaging chat experience across multiple devices without requiring registration.

Code Snippets AI indexes full codebases to deliver contextual insights, auto‑generated comments, and precise snippet recommendations. It tracks LLM usage, supports multi‑model chat, offers role‑based collaboration, and integrates with macOS and Windows via API.

TypingMind unifies ChatGPT, Gemini, Claude, and other LLMs in one interface, enabling parallel chats, project folders, tagging, search, and built‑in tools for documents, images, and code, plus features like agent building, prompt chaining, RAG, voice, canvas, and plugins.

Clerk Chat unifies voice, SMS, WhatsApp, and RCS, deploying real‑time agents for lead qualification and appointment scheduling. It integrates with Salesforce, Teams, and Genesys, supports HIPAA/SOC 2 compliance, and enables 24/7 automated outreach through embedded widgets.

OmniRoute is an open-source AI gateway that routes requests to 236 LLM providers via a single /v1 endpoint, offering multi-provider routing with auto-fallback, token compression, persistent memory, resilience controls, MCP/A2A support, and self-hosted analytics.

CRMChat is a Telegram‑native CRM that unifies lead research, automated outreach, and pipeline management in one dashboard. It supports multi‑account sequences, lead discovery, warm‑up, and integrates with HubSpot or Pipedrive for unified sales tracking.

LLM SEO Monitor tracks keyword rankings and AI-generated SERP results across ChatGPT, Claude and Gemini, highlights content gaps and ranking opportunities, provides competitor analysis, automated alerts, exportable reports and API integrations for workflow automation.

LLM Price Check aggregates LLM API models and provider details into sortable tables and a cost calculator, showing context windows, input/output cost metrics, and quality indicators to help developers and teams evaluate cost–performance tradeoffs.

Jan is an offline ChatGPT alternative for Mac, Windows, and Linux. Enjoy customizable AI assistants, productivity boosts, and secure, exportable data. Integrate with OpenAI equivalent API server and soon-to-come mobile app.

Create a custom AI chatbot without coding. Upload documents or site content to train it, then deploy via a single code snippet on WordPress, Shopify, or any site. Manage chats, export logs, and view engagement analytics.

OurToken.ai is a unified LLM API that allows developers to access models from OpenAI, Anthropic, Google, and others through a single integration point. It simplifies multi-provider deployment with smart prompt routing, centralized key management, and built-in usage tracking for cost optimization.

Firecrawl offers an API that scrapes, crawls, and searches web content, outputting data in clean LLM‑ready formats such as Markdown, JSON, or screenshots. It handles JavaScript-heavy pages, PDFs, and enables interactive browser automation.

paperclip is an open-source, self-hosted AI orchestration platform for creating and managing autonomous companies and agent teams—providing role-based hiring, goal-driven task delegation, budgeting, audit trails, multi-tenant deployment, extensible LLM integrations, and monitoring dashboards.

HammerAI is a private and free AI chat platform for creating and interacting with AI characters in role-play scenarios. The AI model runs locally in the browser for free, ensuring user privacy and security.

LoginLlama is an API that scores each authentication attempt from 0–10, offering block, MFA, or allow actions. It detects IP and user agents, delivers sub‑500 ms responses, and provides dashboards for risk trends and alerts.

AI.LS is a sleek, ChatGPT-powered UI tool replacing Poe, offering a free and online alternative for chat-based AI assistants. Its user-friendly interface facilitates smooth conversational experiences with AI.

AIMLAPI.com offers a unified API endpoint for over 400 AI models spanning chat, image, video, audio, voice, text, 3D, and OCR. It supports sandbox testing, granular access control, batch requests, and an OpenClaw runtime for secure, human‑in‑the‑loop workflows.

LLM Pulse tracks brand visibility and search presence across LLMs (ChatGPT, Perplexity, Google AI), offering prompt tracking and suggestions, citation analysis, visibility scoring and competitor benchmarking, sentiment and response inspection, plus API and reporting exports.

Lightfield.app is an AI-native CRM that auto-captures all customer interactions and builds continuous account context. It generates pipelines, drafts outreach, and scores accounts to reduce manual data entry and prioritize sales actions.

Chattee is an AI app builder that converts plain-English prompts into full-stack web applications with databases, auth, and workflows. It enables instant deployment with scalable hosting while allowing full code export and ownership for rapid prototyping and production.

Chatwith is a no‑code platform that embeds AI chatbots on websites, intranets, and messaging apps. It trains on internal content, connects to 5,000+ apps for real‑time data, supports 95+ languages, offers custom branding, analytics, and API integration.

Create customized software using natural language ideas with the openbmb/chatdev tool's LLN-powered multi-agent collaboration framework.

Chatbase builds and deploys AI customer support agents trained on business data, integrates with CRMs, Zendesk, Slack and WhatsApp, enables automated workflows, human escalation, analytics, multilingual support, and security controls (SOC 2, encryption).

Loman AI is a 24/7 voice agent that handles restaurant calls for pickup, delivery, and reservations, processes payments, syncs with POS and reservation systems, offers real‑time dashboards, and routes complex inquiries to staff.