Cognee gives AI agents persistent long-term memory that survives across sessions, replacing the traditional stack of separate graph, vector, and session databases with a unified engine running on a single PostgreSQL instance. The memory-native API exposes four verbs (remember, recall, forget, and improve) enabling agents to persist context, retrieve cited answers, prune outdated knowledge, and self-improve from feedback. Under the hood, Cognee combines pgvector embeddings with a PostgreSQL-native graph store and cognitive-science-grounded ontology generation, delivering hybrid retrieval that fuses semantic similarity, structural graph traversal, and lexical search in a single query. Integrations span Claude Code, Cursor, LangGraph, OpenAI Agents, and any MCP-compatible client through a dedicated MCP server on port 8001, while the Python and TypeScript SDKs provide direct programmatic access. The platform supports swappable backends including Neo4j, FalkorDB, Qdrant, ChromaDB, Weaviate, Milvus, and LanceDB for teams with existing infrastructure. Built-in OpenTelemetry tracing, an experimental dashboard with knowledge graph visualization, multi-tenant user isolation, and audit trails ensure production readiness. Deploy via Docker Compose with optional profiles for PostgreSQL, Neo4j, Redis, and the web frontend. Reached v1.0 in April 2026 with 30,000+ stars. 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.

BitRouter is a context-aware LLM router that learns which model delivers the cheapest successful outcome per workflow step, cutting agent costs by up to 80% while maintaining 96% quality versus all-frontier baselines. Point any agent runtime at http://localhost:4356 with a one-line OPENAI_BASE_URL change and BitRouter routes to OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, Moonshot, MiniMax, Nvidia, and any OpenAI-compatible endpoint simultaneously, normalizing authentication, streaming, and cross-protocol translation between wire formats. The act-observe-evaluate-learn loop traces every hop with cost, tokens, and latency attribution, scores each decision against a versioned policy-lock.yaml, then tightens routes automatically with no LLM judge in the path. Native MCP gateway auto-discovers tools from connected servers and makes them routable and governed alongside model calls. Agent Client Protocol integration enables the TUI to manage Claude Code, Codex, OpenCode, OpenClaw, Gemini, and Copilot sessions in real time with inline tool-call approval and live streaming. Built-in guardrails inspect, redact, or block risky content before requests leave your network. Virtual keys scope API access per agent or user without exposing upstream credentials. Per-agent spend caps and loop guards contain runaway cost automatically. Multi-account failover reroutes mid-run so rate limits never re-pay completed work. Ships as a single Rust binary via npm or Cargo. 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.

Turn company knowledge into structured courses in minutes: ClassroomIO's AI course builder takes your documents, policies, or topic outlines and generates complete lessons with exercises using Gemini, GPT-4o, or Claude — then an in-lesson AI tutor helps employees study the material at their own pace. The SvelteKit 5 and Hono API architecture backs a platform purpose-built for employee compliance training, customer education, and partner certification programs. Programs group courses into cohorts with team management, progress tracking, and goal setting. Live Kahoot-style quizzes drive real-time engagement during training sessions with automatic scoring and leaderboards. Exercises support multiple question types with automatic grading for multiple choice and AI-assisted evaluation for open-ended responses — teachers review and override all AI decisions. Branded certificates with custom IDs reward course completion. Custom domain mapping through Cloudflare lets organizations serve their learning portal under their own brand. MinIO provides S3-compatible storage for documents and video uploads. The REST API and signed webhooks enable programmatic enrollment and completion tracking, while an MCP server on npm supports AI-native authoring workflows. An embeddable widget drops the course catalog onto any website. Better Auth handles sessions and OAuth with optional SSO. 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.

Kokoro-FastAPI turns text into natural-sounding speech across eight languages by serving the 82-million-parameter Kokoro-82M model through an OpenAI-compatible REST API, so any existing OpenAI SDK client can generate audio by just changing the base URL. With over 5,300 GitHub stars since December 2024, the fully Dockerized FastAPI server covers American English, British English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese with language-specific phoneme processing. Inline voice mixing blends multiple profiles using weighted ratios like af_bella(2)+af_heart(1), automatically normalizing weights and caching combined voicepacks as PyTorch tensor files for reuse. Audio streams in real time over HTTP with configurable chunk sizes, or generates complete files in MP3, WAV, OPUS, FLAC, AAC, or PCM formats with speed control from 0.25x to 4.0x. Per-word timestamped captions with speaker-tagged voice labels enable subtitle generation for podcasts, audiobooks, and accessibility workflows. Pre-built Docker images support NVIDIA GPU acceleration via CUDA, experimental AMD GPU inference via ROCm, and CPU-only deployment on linux/amd64 and linux/arm64 architectures, with Apple Silicon MPS support available through direct UV execution. The integrated web interface at port 8880 provides browser-based speech generation, while the Swagger UI at /docs exposes the full API reference. Debug endpoints report system statistics for monitoring inference load. 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.

With 3,100+ GitHub stars, CyberScraper 2077 replaces brittle CSS selectors and XPath queries with natural language data extraction powered by Large Language Models. Users paste a URL, describe the data they want in plain English, and the AI extracts structured results from any website — no HTML parsing knowledge required. The tool supports three LLM backends: OpenAI GPT models for maximum accuracy, Google Gemini for cost-effective extraction, and local Ollama instances for fully private scraping where URLs and data never leave your server. Built on Python asyncio with Playwright browser automation, it handles concurrent page fetching with content-based and query-based LRU caching to minimize redundant API calls. The Streamlit web interface runs on port 8501 and provides one-click export to JSON, CSV, HTML, SQL, Excel, and direct Google Sheets upload. Tor network integration routes requests through onion routing for anonymous scraping of both clearnet and .onion hidden service sites with automatic circuit management and stream isolation. Stealth mode randomizes user agents, manages cookies, and controls JavaScript execution timing to bypass bot detection systems. Multi-page scraping navigates through paginated results with automatic URL pattern detection. Docker deployment packages all dependencies including Playwright browsers into a single container. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Casibase lets organizations build AI-powered knowledge bases that answer questions from their own documents, connecting to 30+ model providers through a unified admin interface with RAG retrieval and multi-agent orchestration via MCP and A2A protocols. The platform plugs into OpenAI GPT-4o, Anthropic Claude, Meta Llama, Google Gemini, DeepSeek, Ollama local models, HuggingFace, Azure OpenAI, and additional providers, while embedding APIs from OpenAI Ada and Baidu handle vector representation of ingested documents. Document ingestion parses TXT, Markdown, DOCX, PDF, CSV, XLSX, and PPTX files with intelligent chunking strategies for optimal retrieval accuracy. The built-in chat interface provides real-time AI conversations with manual session handover for human agent escalation, and comprehensive chat session logging enables audit trails for compliance. Enterprise identity management integrates Casdoor for Single Sign-On supporting GitHub, Google, WeChat, and OIDC providers with fine-grained access control via the Casbin permission engine. The multi-tenant architecture supports isolated knowledge bases per organization with role-based user management and configurable storage, model, and embedding providers per tenant. The React frontend with Ant Design v5 provides a polished admin dashboard for managing providers, knowledge stores, chat sessions, and user access, while the Go backend with Beego framework handles API logic with MySQL or MariaDB persistence. 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.

With over 330 GitHub stars and described as "OpenRouter, but for agent tools instead of models," Treg is the unified tool registry that gives your AI agent one base URL, one token, and instant access to approximately 2,800 cataloged endpoints across 56 providers — SEO and backlink analysis via Semrush and Moz, social media intelligence from TikTok and Instagram, people and company enrichment through Crunchbase and Hunter, media buying, scraping, and SERP data — all priced per call from fractions of a cent with no provider signup required. The FastAPI backend with PostgreSQL stores credential bindings and injects them server-side into every proxied request, ensuring API keys and OAuth tokens never touch the agent or local machine while every call is audit-logged. Teams register their own paid API accounts, OAuth connections, vendor CLIs like Stripe, GitHub CLI, Vercel, and gcloud, plus custom SKILL.md definitions — all callable by every teammate's agent through a single treg token with automatic credential injection. The evidence-based tool selector shows success rate, response speed, and last-seen timestamp for each provider, so agents pick tools on measured performance rather than guesswork. Bring-your-own-key routes bypass metering entirely, and the one-dollar free credit on every new team lets agents start calling immediately. The Vue.js web dashboard provides team management, audit logs, catalog browsing, and guided onboarding. Self-host with pip install tools-registry[server] 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.

Describe a component in natural language and watch it render: OpenUI, from Weights & Biases, is an open alternative to Vercel's v0. Type a prompt like "a dark-themed dashboard with a sidebar and charts" and the LLM renders working HTML with Tailwind styling live in the browser. You then iterate conversationally, asking for changes until the design is right, and convert the result to React, Svelte, or Web Components for use in a real project. The backend is Python with LiteLLM routing, so it works with OpenAI, Anthropic, Gemini, Groq, and Mistral API keys, or fully offline against local Ollama models, including vision models like LLaVA that can generate UI from screenshot input - feed a screenshot and the model reproduces or riffs on an existing interface. Generated markup is inspectable at any point, with light and dark mode toggles, theme selection, and responsive previews across device sizes. The practical effect is compressing the mockup-review-revise loop from hours to minutes: a described layout renders in seconds and iterates through follow-up prompts, and because output converts to real framework code, prototypes feed directly into production codebases instead of staying trapped in a design tool. Self-hosting keeps unreleased product interfaces and prompts on your own server, and LiteLLM routing lets you pick the model per task - a cheap fast model for rough drafts, a stronger one for final passes, or free local models for unlimited experimentation.

Agentic SOC Platform compresses hours of manual security analysis into seconds by deploying specialized AI agents that autonomously triage, investigate, and enrich security alerts. The Python/Django backend processes SIEM webhooks through Redis Streams into a modular pipeline where LangGraph-orchestrated agents extract IOCs, correlate signals, and generate Cases with severity, confidence, impact, priority, and structured verdicts. The built-in SIRP provides full case management with Alerts, Artifacts, Enrichments, Tickets, and a Knowledge base that accumulates institutional memory for both human analysts and LLM agents. Native Splunk and Elasticsearch/Kibana integrations deliver unified log search through a standardized interface so agents and analysts share identical security context. The playbook engine combines traditional SOAR automation with AI-powered investigation — launching threat hunting agents, knowledge extraction, threat intelligence enrichment, and CMDB lookups from a single orchestration layer. MCP Plugin support exposes ASP capabilities to Claude Code, Codex, and OpenCode, enabling external AI agents to operate cases, search logs, query threat intelligence, and write custom modules directly. Python Modules adapt new alert sources while Playbooks orchestrate LLM analysis and automated response actions, scaling the platform with your security scenarios. Deploy via Docker Compose with all data staying inside your network. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 24,000 GitHub stars and origins in the MemGPT research paper on virtual context management, Letta has evolved into the leading open-source platform for building AI agents that maintain persistent memory, identity, and continuity across sessions rather than operating as stateless prompt-response loops. The core architecture uses memory blocks — structured, labeled text chunks that reside permanently in the agent's context window — allowing agents to programmatically rewrite their own memory, learn new skills, and improve through a sleeptime dreaming process that runs reflection and memory organization during idle periods. The self-hosted App Server deploys via Docker and exposes a WebSocket API on port 4500, letting the TypeScript Agent SDK connect from any application using local, remote, or cloud backends. Agents support git-versioned memory through MemFS where every memory change is tracked and auditable, multi-agent communication via subagents, scheduled tasks, and integration with messaging platforms including Slack, Discord, Telegram, WhatsApp, and Signal. The platform is fully model-agnostic, routing to OpenAI, Anthropic, xAI, or self-hosted open-weight models through Ollama depending on cost, performance, and data residency requirements. The Agent File format serializes complete agent state — memory, skills, prompts, and conversation history — into portable snapshots. Desktop applications for macOS, Windows, and Linux provide native interfaces alongside the terminal CLI and web chat at chat.letta.com. 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.

OpenCode Manager is a mobile-first command center for AI coding agents. Install the PWA on your phone or tablet and you get real-time streaming chat, multi-repository Git operations, and scheduled automation right in your pocket. Git integration handles SSH-authenticated repo cloning, worktree management, unified diffs, and branch operations across all your projects in one dashboard. Chat with coding agents through Server-Sent Events streaming that supports slash commands, @-mentions for files, Plan and Build modes, and Mermaid diagram rendering for architecture discussions. Schedule reusable prompts to run against any repository on intervals or cron expressions, with each run tracking history and linking to sessions so you can pick up exactly where automation left off. MCP server configuration adds local and remote HTTP servers with OAuth support, plugging into the broader Model Context Protocol ecosystem. A dedicated assistant workspace provides an isolated AI environment with auto-provisioned skills for managing schedules, notifications, and settings. Multiple AI providers are supported including Anthropic, GitHub Copilot, and OpenAI-compatible services, each configurable with custom system prompts and granular tool permissions. Push notifications alert you to session events, agent questions, errors, and task completions across all managed repositories.

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.

Originated as Alibaba Group's official internal AI code review assistant serving tens of thousands of developers and identifying millions of code defects over two years before open-sourcing in May 2026 — now at 21,000+ GitHub stars — Open Code Review is the production-hardened platform that proves enterprise-grade code review can be fully open-source under Apache 2.0. The hybrid architecture separates deterministic engineering pipelines (file selection, diff parsing, rule matching for NPE, thread-safety, XSS, and SQL injection across 10+ languages) from LLM-powered agent reasoning with tool-use capabilities including FileRead, CodeSearch, and cross-file context inspection, consuming approximately one-ninth the tokens of general-purpose coding agents while delivering line-level precise comments with severity and confidence scoring. The bundled web dashboard (port 4173) provides review management, findings triage, result browsing, and direct GitHub posting without external dependencies, while the session viewer (port 5483) renders full LLM request/response traces for debugging and auditing. Integration spans GitHub Actions, GitLab CI, GitFlic CI, and Gerrit with delegation mode enabling Claude Code, Cursor, and other AI agents to leverage OCR's engineering logic alongside their own LLM reasoning. Supports OpenAI, Anthropic, Google Gemini, DeepSeek via built-in providers plus Ollama and vLLM for air-gapped deployments. 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.

Paste one SQL query result into a browser and get an interactive entity-relationship diagram instantly, with no installations, no credentials, and no account required. ChartDB's "Smart Query" runs a single statement in your existing database client that exports table definitions, relationships, indexes, and column types as JSON metadata, meaning the application never touches your database passwords. The canvas renders draggable entities with cardinality markers, collapsible grouping areas, and sticky notes for documentation. AI-powered DDL export generates migration scripts between dialect pairs like PostgreSQL to MySQL or SQLite to CockroachDB, analyzing your schema to produce target-specific DDL with correct type mappings and constraint translations. Import paths cover Smart Query JSON, raw DDL scripts, and DBML files from tools like dbdiagram.io. The AI layer connects to OpenAI or any compatible inference server including local vLLM instances running models like Qwen2.5-32B. Database coverage includes PostgreSQL (with Supabase and Timescale extensions), MySQL, SQL Server, MariaDB, SQLite (with Cloudflare D1), CockroachDB, ClickHouse, and Oracle. Exports to SVG with inline styles or SQL DDL in any target dialect. Ships as a React/Vite frontend behind Nginx in Docker, deployable on RepoCloud with dedicated VPS resources under the AGPL-3.0 license.

Achieving 98.4% Recall@5 on LongMemEval-S without a reranker, AKB is the agent-native knowledge infrastructure giving Claude Code, Cursor, Windsurf, and any MCP-aware agent persistent organizational memory — a drop-in replacement for Confluence or Notion where AI agents read and write directly rather than scraping human-formatted pages. Documents are stored as Markdown with YAML frontmatter in Git bare repositories (full version history, branching, diff), while PostgreSQL 16 serves as source of truth for chunk text, metadata, and BM25 vocabulary, with dense embeddings handled by a pluggable vector store (pgvector default, Qdrant optional, or managed Seahorse). Agents interact through 20+ MCP tools — akb_put, akb_search, akb_browse, akb_relations, akb_sql, akb_edit, akb_history — performing hybrid dense plus BM25 search fused via Reciprocal Rank Fusion in one call. The URI graph (depends_on, related_to, implements relations) lets agents traverse knowledge connections without external graph databases. Multi-tenant vault isolation is enforced at the PostgreSQL ACL level with per-user roles and SET LOCAL ROLE for SQL sandboxing. Event fanout streams structured events to Redis Streams for external consumers (synthesis bots, digest agents, audit trails), and a hash-chained append-only audit log integrates with enterprise SIEMs. Ships with agent plugins for Claude Code and Codex (session capture, wiki ingest, lifecycle hooks), Kubernetes kustomize manifests, and Open Knowledge Format export. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSL 1.1 licensed (free under 100 seats, auto-converts to Apache 2.0 after four years).

Backed by 56,000+ GitHub stars and over 240 million Docker pulls, LiteLLM delivers the open-source AI gateway trusted by Netflix, Lemonade, Rocket Money, and thousands of engineering teams to route every LLM request through one unified API. The Rust-core gateway adds sub-millisecond overhead per request with 8ms P95 latency at 1,000 RPS, 15x throughput improvement and 11x lower memory footprint compared to Python-only proxies. A single OpenAI-compatible endpoint connects to 100+ providers and 1,800+ models spanning OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Vertex AI, Hugging Face, vLLM, Nvidia NIM, Ollama, and Mistral with day-zero support for new model releases. The Auto Router V2 classifies request complexity across four tiers using rule-based scoring, semantic keyword matching, and adaptive Thompson sampling to route each request to the most cost-effective model without API calls or training data. Virtual API keys enable multi-tenant governance with per-team, per-user, and per-project cost tracking, budget caps with automatic fallback rerouting, and role-based access control. Built-in guardrails provide PII masking, prompt injection detection, and model-graded evaluation before requests reach providers. The Agent Gateway extends routing from model calls to agent workflows with MCP server integration. Observability integrates with Langfuse, Arize Phoenix, OpenTelemetry, and MLflow for complete request tracing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Kotaemon is a document QA platform that combines advanced RAG techniques with a clean Gradio-based web interface for chatting with your documents. Built by Cinnamon, the Python backend supports any LLM provider including OpenAI, Azure OpenAI, Cohere, Groq, and local models via Ollama and llama-cpp-python, with a model management panel for configuring LLM and embedding providers from the UI. The default hybrid RAG pipeline combines full-text keyword retrieval with vector similarity search and applies re-ranking to ensure optimal result quality, while multi-modal document parsing extracts content from tables and figures alongside text. Advanced citations link every answer to specific source passages with relevance scores, viewable directly in the built-in PDF viewer with highlighted text spans. GraphRAG indexing via NanoGraphRAG, LightRAG, or Microsoft GraphRAG builds knowledge graphs from document collections for relationship-aware retrieval. Agent-based reasoning supports question decomposition for multi-hop queries using ReAct and ReWOO strategies. Multi-user authentication organizes documents into private and public collections with sharing and collaboration features. The platform supports Docker deployment in lite, full, and Ollama-bundled variants, runs on port 7860, and stores application data in a persistent volume. MCP tool integration enables external system connections for extended retrieval capabilities. On RepoCloud, deploy Kotaemon on a dedicated VPS with Docker, root SSH access, and complete control over your document AI infrastructure, all under the Apache 2.0 license.

Speakr transforms audio recordings into organized, searchable, AI-enhanced notes with speaker recognition that identifies who said what across your entire recording library. The Python/Flask backend with Vue.js 3 and Tailwind CSS frontend deploys via Docker on port 8899, offering multiple transcription engines through auto-detected connectors: WhisperX for local processing with speaker diarization and voice embeddings, OpenAI Whisper and GPT-4o-transcribe, Mistral Voxtral for cloud diarization, AssemblyAI for multi-hour files, and any custom ASR webservice. Speaker voice profiles use embedding comparison to recognize individuals across different recordings automatically, while custom vocabulary biases the transcriber toward domain-specific jargon. The AI layer goes well beyond transcription: customizable summaries with per-recording, per-tag, and per-folder prompt templates; event extraction surfacing action items and calendar events; per-recording chat with streaming responses; and Inquire Mode for semantic search and natural-language queries across your entire library simultaneously. Smart tags execute custom AI prompts on transcripts for automatic categorization. The REST API with Swagger documentation supports signed webhooks integrating with n8n, Zapier, and Make. Auto-export pushes to Obsidian and Logseq, auto-processing watches directories, and the installable PWA provides mobile-first, offline-capable access with share-target support. 3,600+ stars since May 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.