Prototype multi-agent AI systems without writing orchestration code: AutoGen Studio is Microsoft's low-code interface over the AutoGen AgentChat framework. You compose teams of LLM-powered agents in a visual Team Builder, either by drag-and-drop from a component library or by editing the declarative JSON specification directly. Each agent gets a model, a prompt, tools (Python functions), and the team gets termination conditions and an orchestration pattern, sequential or LLM-driven. The Playground runs teams interactively with live message streaming between agents, a visual control-transition graph, tool-call and code-execution tracking, and pause/stop controls, which makes it a practical debugger for agent behavior. Finished teams export as JSON for use in any Python application via the TeamManager class, or serve as an API endpoint. Any OpenAI-compatible model endpoint works, including local servers like Ollama or vLLM. Microsoft labels it a research prototype: use it for prototyping and evaluation, and build production systems on the underlying AutoGen framework.

GoRaven transforms AI chat from a question-answer window into a full engineering workstation where agents read files, write code, run shell commands, query databases via MCP tools, and deliver structured results — orchestrating across OpenAI, Claude, DeepSeek, Gemini, Qwen, GLM, and Ollama with task-based routing that allocates the right model for each job based on cost and capability. Built on a Go backend using the Freedom framework with Iris HTTP and a React/TypeScript frontend powered by Vite and Tailwind CSS, each user operates in an isolated workspace with team-shared project areas and centrally managed model quotas. The skill marketplace packages prompts, scripts, and workflows as reusable installable units with automatic dependency resolution and centralized versioning. MCP toolchain integration connects agents to internal APIs, databases, private services, and CLI tools so they query data, invoke services, and trigger actions directly. RAG-powered knowledge bases ingest policies, documentation, and business data for real-time retrieval during planning, coding, and Q&A with source attribution. Long-running task support decomposes complex work through a main agent coordinating sub-agents that execute in parallel across sessions. Plugin hooks inject custom logic at conversation start and end, tool calls, and SSE event streams without forking core code. The operations dashboard tracks usage metrics, model consumption, and team activity. Supports SQLite, MySQL, or PostgreSQL with Redis or local memory caching. Deploy with a single Docker command. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Running AI agents in production takes more than a model call: Omnara supplies the durable runtime, tools, approvals, and complete event history around any model, on your own machines. You define an agent once in a small YAML file: instructions, a model from OpenAI, Anthropic, OpenRouter, Bedrock, LiteLLM, Ollama, or your own endpoint, and the machines it may use. Launch agents from the REST API, the TypeScript SDK, the command line, or the dashboard, then stream every event live or receive it as a webhook while the agent works. Agents run shell commands and edit files on sandboxes from twelve providers, or on your own laptops, VMs, and containers through a daemon that connects outward, so no inbound ports or SSH keys are exposed. Every step is written to Postgres as an event log, which means an agent survives crashes, restarts, and disconnected machines and resumes exactly where it stopped. Tool permissions can run immediately, ask a person first, or block outright, and agents can start subagents, follow cron schedules, and keep shared memory files between conversations. Teams meet the agents where they already talk: mention the bot in Slack or Discord, or let a GitHub pull request trigger a review, with questions and approvals handled in the thread. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.

When an AI agent goes wrong at step seven of twelve, Opik, an open-source LLM observability platform, shows the exact trace, tool call, and prompt behind it, then scores your fix against test datasets. Full trace trees capture every LLM call, retrieval step, and tool execution, and you can annotate traces and spans with feedback scores in the UI or through the SDK. Native integrations for OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, Google ADK, and DSPy, plus OpenTelemetry for any language with an OpenTelemetry SDK, feed traces in, or add the @track decorator to your own functions. Datasets and experiments compare prompt and model versions, scored by LLM-as-a-judge metrics for hallucination, moderation, and RAG relevance, with a PyTest integration to run evaluations in CI. A Prompt Playground tests prompts across models, and the Agent Optimizer SDK helps improve prompts and agents. Production dashboards track feedback scores, trace counts, and token usage, online evaluation rules score live traces, and optional guardrails add safety checks. An MCP server lets Claude Code, Cursor, VS Code Copilot, Codex, or opencode read traces and run evaluations from chat. Run it yourself with the ./opik.sh script on Docker Compose, or a Helm chart on Kubernetes, so trace data stays in your infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Character-based chat and storywriting with large language models: TavernAI is the open-source frontend that leaves model choice to you. It generates no text itself; it connects to the backend of your choice - OpenAI (including GPT-4), Anthropic Claude, KoboldAI and KoboldCpp, Oobabooga's Text Generation Web UI, NovelAI, Ollama, and the crowdsourced Horde - so cost, model quality, and content policy are decided by your backend, not the interface. Characters are defined by portable card files in PNG or JSON format with personality, scenario, and example dialogue, and tens of thousands of community-made cards from sites like Chub.ai import directly. Conversations support group chats with multiple characters, a story mode for long-form writing, message swiping to branch between alternative responses, and full editing of any message. World Info injects lore into context when keywords trigger, keeping long roleplays consistent. Themes, custom backgrounds, and configurable generation settings round out the interface. It runs on Node.js, and the SillyTavern project began as a fork of it.

Live web search plus an LLM of your choice: Farfalle is an open-source, self-hosted answer engine in the Perplexity mold. Queries route through one of several search providers - self-hosted SearXNG for a fully independent stack, or Tavily, Serper, and Bing APIs - and the model composes a cited answer from the retrieved results. Model flexibility is the core design: run llama3, mistral, gemma, or phi3 locally through Ollama for zero per-query cost and full privacy, use cloud models like GPT-4o or Groq-hosted Llama 3 for speed, or route to any provider via LiteLLM. An Expert Search mode uses an agent that plans a multi-step search strategy and executes it for harder questions, and chat history keeps prior research sessions available. The stack is a Next.js and shadcn/ui frontend over a FastAPI backend with Redis rate limiting, shipped as a pre-built Docker image. A browser search-engine entry pointing at your instance makes it the default search from the address bar. Paired with SearXNG and Ollama, the whole pipeline runs with no external API at all.

WeKnora turns scattered corporate documents into a searchable, reasoning-capable knowledge asset that your team can query in plain language and receive cited, sourced answers. Upload PDFs, Word files, web pages, Feishu wikis, Notion databases, Yuque docs, GitLab repositories, or RSS feeds into structured knowledge bases, and three distinct modes make the content actionable: RAG Quick Q&A retrieves relevant chunks and generates answers with source citations; the ReAct Agent autonomously orchestrates multi-step reasoning across knowledge retrieval, MCP tool calls, web search, and sandboxed code execution to produce comprehensive research reports; and Wiki Mode deploys LLM agents to distill raw documents into an interlinked markdown knowledge base with an interactive knowledge graph, revision history, and one-click rollback. Connect 20+ LLM providers including OpenAI, DeepSeek, Qwen, Claude, and local Ollama models without vendor lock-in, and choose from seven vector database backends (Qdrant, Milvus, Weaviate, and more) for embedding storage. Enterprise features include four-tier RBAC with per-resource ownership and per-workspace audit logs, AES-256-GCM credential encryption, scoped API keys, Langfuse observability tracing for every agent loop and tool call, and a runtime task-queue dashboard for worker-pool governance. Cross-session long-term memory preserves conversational context across interactions. The Agent Skills catalog lets teams install and share sandboxed scripts executed in Docker or E2B containers. A Chrome Extension captures web content directly into knowledge bases. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Edict is a multi-agent orchestrator that runs every AI request through a court-style chain: a crown prince agent triages it, a planning department drafts the work, a review department can veto the plan, and specialist ministries execute what survives. Casual chat gets a direct reply, while real commands become kanban tickets whose titles are scrubbed of file paths and metadata. A vetoed plan returns for rework; an approved one is dispatched in parallel to ministries for finance, documentation, engineering, compliance, infrastructure, and HR. Commands arrive through Feishu, Telegram, or Signal channels configured in OpenClaw. The dashboard shows cards by state with heartbeat badges and stop, cancel, and resume controls, plus a department monitor and a memorial archive that turns finished work into five-phase timelines you can copy as Markdown. Nine edict templates add parameter forms and cost estimates, an officials panel ranks agents by merit score while tracking token spend, and per-agent model switching restarts the gateway in about five seconds. Agent thinking, tool calls, and results stream live. A permission matrix limits who may message whom, illegal state jumps are rejected, and every transition lands in an audit log. Worked examples cover competitive analysis, code review, and weekly reports. Dashboard login protects the console, and a systemd unit keeps it running across reboots. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

An 8MB Go binary that boots in under one second, uses less than 10MB of RAM, yet delivers full AI agent capabilities across 16+ chat platforms simultaneously. PicoClaw connects to Telegram, Discord, Matrix, IRC, Slack, WeCom, DingTalk, WeChat, LINE, and QQ while supporting LLM providers spanning OpenAI, Anthropic, Gemini, DeepSeek, AWS Bedrock, Azure, and local models via Ollama. Native Model Context Protocol support enables standardized tool integration, and the built-in smart routing engine directs simple queries to lightweight models to reduce API costs while sending complex tasks to capable models. Tool capabilities include secure shell execution, filesystem access, web search, cron scheduling for recurring tasks, and sub-agent spawning with status tracking. Gateway mode transforms PicoClaw into a full AI backend with REST API endpoints accessible from any client. The Skills system loads hierarchical behavior definitions from SKILL.md files, enabling customizable agent personalities and workflows. Compiles for x86_64, ARM64, ARMv7, RISC-V, MIPS, and LoongArch, making it deployable on hardware as cheap as a $10 Sipeed LicheeRV Nano. Achieved nearly 30,000 stars within six months of its February 2026 release. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

CPA Manager Plus is a self-hosted observability dashboard and management panel that tracks every AI request flowing through your CLI Proxy API gateway, breaking down failures, costs, and account health across providers like OpenAI, Anthropic, xAI, and Codex in one interface. When a request fails, drill into the persistent history to see status codes, affected models, latency, and redacted failure evidence without exposing raw response bodies. The cost analytics engine breaks down token consumption and estimated spend by model, provider, account, API key, project, channel, and time range while tracking input, output, reasoning, cache, and service-tier pricing semantics separately. Model prices sync automatically from models.dev with LiteLLM and OpenRouter fallbacks, and you can add local overrides for aliases or internal models. For teams running Codex or xAI accounts, the health inspector reads quota windows, reset evidence, credential state, and workspace status on a configurable schedule, routing credential failures into an action queue for review rather than letting them silently degrade throughput. Deploy the Lightweight Panel to replace your existing CPA management UI without adding another service, or run Full Mode as a single Docker container that adds the Manager Server with persistent SQLite storage for request history, historical analytics, and automated account inspections. Export or import request history as JSONL for external analysis, and back up the SQLite files alongside your encrypted management keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Instead of a separate chatbot for each channel, Synaplan runs one self-hosted AI assistant for your team, website visitors, WhatsApp line, and inbox, and shows what every reply cost. In the web app, connect OpenAI, Anthropic, Gemini, Groq, Mistral, xAI, Hugging Face, or local Ollama. Each kind of work gets its own model, from chat and image to video and audio, and every answer carries a Free, Low, Mid, or High cost badge. A planner splits a big request into a task graph and sends each step to the model that fits. On your website, one script tag adds a chat widget, and a human operator can take over any conversation live. On WhatsApp Business and email, the assistant replies on the channel where the question arrived. Behind every channel sits one knowledge base: upload PDFs, Word and Excel files, or images with OCR, and semantic search feeds them into answers. Saved tasks run on demand or on a schedule, approvals pause any action that writes, and watched pages mail you a diff when a URL changes. Connections reach Microsoft 365, Dropbox, Nextcloud, ownCloud, WebDAV, CalDAV, Jira, and Confluence. An MCP server and an Anthropic-compatible endpoint let Claude, Cursor, and Claude Code use your instance. Users and groups share folders and assistants, and admins see usage and health. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Kodus AI automates pull request code review with inline AI comments across GitHub, GitLab, Bitbucket, and Azure DevOps, supporting any LLM provider at cost with zero token markup. The multi-service TypeScript architecture deploys via Docker Compose, running an API server, background worker, webhooks service, and React dashboard backed by PostgreSQL with pgvector, MongoDB, and RabbitMQ. Integration covers both cloud platforms and their enterprise flavors (GitHub Enterprise Server, GitLab Self-Managed, Bitbucket Data Center) using standard OAuth flows and webhook signing to keep the review loop entirely inside your network. The platform is model-agnostic with Bring Your Own Key support for Claude, GPT, Gemini, Llama, and any OpenAI-compatible endpoint including locally-hosted models. Custom review rules combine your team's coding standards with requirements pulled from Jira, Linear, and Notion, automatically checking every PR against documented specifications. The CLI enables local reviews against working trees, staged diffs, branches, or specific commits, integrating into CI/CD pipelines as pre-merge gates. Source code is never stored and never used for model training, with all data encrypted in transit and at rest. 1,270+ stars and 129+ releases since March 2025. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Pagesift converts messy web pages, PDFs, and Office documents into clean Markdown and structured JSON that language models can actually use, from one self-hosted binary you run yourself. Call it the way you already call Firecrawl: the HTTP API speaks the Firecrawl v1 and v2 formats, so existing scrape, crawl, and batch jobs point at your server instead, and a Jina Reader style endpoint answers simple /r/ URL requests. Scrape a single page, submit batches, or crawl whole sites with sitemap support, focused crawling by query, robots.txt respect, and per-host rate limits by default. Headless rendering kicks in only when a page needs JavaScript, keeping plain pages fast. Documents work offline too: Word, Excel, PowerPoint, EPUB, and CSV files become Markdown with titles, links, images, and publication metadata attached. Jobs persist so long crawls survive restarts, webhooks report completions, and per-API-key limits and quotas keep multi-tenant use civilized, with Prometheus metrics and a health endpoint for operators. AI agents can drive the same engine directly through the bundled MCP server over stdio or HTTP, while developers get Python, Node, and Rust libraries. Memory stays bounded under load by design, sized from container limits rather than hope. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Memory that survives the session: Hindsight extracts facts, entities, and timestamps from everything an AI agent retains, then lets the agent search or reason over it later. Adding it to an existing LLM client takes a two-line wrapper, and more than 60 integrations cover Claude Code, Cursor, LangGraph, CrewAI, and n8n. Every bank also exposes its own MCP endpoint. Retain sends text, images, or files through an LLM that extracts facts, timestamps, entities, and relationships. Recall runs semantic, keyword, graph, and temporal searches in parallel, merges them with reciprocal rank fusion, reranks with a cross-encoder, and trims to a token budget. Reflect reasons across memories for questions that need synthesis, shaped by per-bank skepticism, literalism, and empathy traits. In the background, related facts consolidate into observations that keep exact quotes and proof counts and are refined, never silently overwritten. Mental models and wiki-style knowledge pages hold standing answers that rewrite themselves as the bank learns. Each user, agent, or project gets an isolated bank with no cross-bank leakage, and Memory Defense redacts or blocks secrets and PII against 45 patterns. The Control Plane adds a Recall Analyzer with traces, a memory constellation graph, and a knowledge page editor. Extraction and reasoning can run on 25+ LLM providers, including local Ollama and llama.cpp. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Describe what you want in plain language and get real SQL against your real schema: SQL Chat is an open-source, chat-based SQL client from the Bytebase team. Instead of writing queries in a traditional editor, you connect a database and describe what you want in plain language; the AI reads your schema automatically, generates SQL that references real table and column names, executes it, and returns tabular results in the conversation. Follow-up messages refine the query, so exploration becomes a dialogue - narrow a result set, add a join, change an aggregation - without retyping statements. It supports MySQL, PostgreSQL, SQL Server, TiDB Cloud, and OceanBase from one interface, and covers modification as well as reads: insert, update, and delete operations phrased conversationally. Built with Next.js and TypeScript, it deploys as a single stateless Docker container in single-user mode - connection profiles live in the browser, so there is nothing server-side to maintain. A custom AI endpoint setting routes inference through any OpenAI-compatible API, including self-hosted models, and an optional database-backed mode adds accounts and quotas for offering the tool to a team. MIT-licensed.

Hermes Workspace serves as a dedicated command center for orchestrating autonomous AI agents, combining multi-model conversational flows with direct system execution in a unified web environment. Operators can execute multi-turn agent missions while observing live reasoning paths, tool dispatches, and file system mutations as they occur in real time. The built-in memory browser lets users inspect episodic recollections, search indexed agent knowledge bases, and edit persistent recall records directly from the interface. A comprehensive skill catalog provides instant activation and parameter tuning for over one hundred modular tool capabilities, ranging from web scraping to programmatic code generation. The embedded browser terminal delivers pseudoterminal sessions alongside running agents, enabling human operators to execute diagnostic commands and inspect project workspaces without switching windows. Conductor and Swarm management panels coordinate parallel sub-agent workers to break down complex research directives into asynchronous subtasks with automated status tracking. Integrated model switching allows teams to route individual execution steps dynamically between Anthropic Claude, OpenAI, OpenRouter, and self-hosted Ollama instances. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Your documents change every day, and your RAG answers should change with them: Serviette keeps a chat and REST API continuously in sync with the files you point it at, no re-indexing jobs to remember. Point it at a local folder, Google Drive, S3 or MinIO bucket, SharePoint library, or even an FTP or WebDAV share, and edits, additions, and deletions flow into the index in real time. One YAML file, or the interactive wizard, chooses among eight vector databases, from embedded DuckDB with zero setup to pgvector, Qdrant, Milvus, Chroma, Weaviate, Pinecone, or MongoDB Atlas. Text, Office files, PDFs with tables, and scanned images are parsed and answerable by default, with audio and video joining when you add the keys. Embeddings can run fully locally with no credentials, and keyless answers simply quote the retrieved passages with their sources. The indexer and the stateless server scale independently, the server shards across workers with one config line, and both a ChatGPT-style web chat and a versioned /api/v1 retrieval API answer on the same port. A free license key from Pathway activates the engine, and benchmarks cover corpora up to 50 GB of text. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.