Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.

Give Claude Code a video perception layer that extracts frames, transcribes audio, and lets Claude answer questions about local videos or YouTube URLs.

Runs an existing coding agent behind Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat, or HTTP so teams can invoke real agent sessions from chat without rebuilding the agent stack.

Connect agents and IDE assistants to Shopify docs, API schemas, code validation, and store-management workflows through Shopify's official toolkit.

Scaffold, build, and run MCP servers from a predictable Python project layout with tools, prompts, resources, auth, and OpenTelemetry hooks.

Use LlamaAgents to define async Python workflow steps, coordinate document-centric agent pipelines, and expose those workflows as services, clients, or deployable agent apps.

Stand up Solace Agent Mesh projects where agents delegate tasks, exchange events, call tools, and coordinate multi-step workflows through an event mesh.

Index private text into graph-backed retrieval structures, tune prompts, and query the resulting knowledge graph for RAG workflows.

Use Atmosphere to build JVM agent gateways that stream over WebSocket, SSE, gRPC, WebTransport, MCP, A2A, and AG-UI with governance hooks.

Store raw multimodal data, embeddings, and vector-search indexes in Deep Lake so agents can retrieve grounded context for RAG and analysis workflows.

Use assistant-ui to build production React chat interfaces with reusable threads, runtimes, message components, and model/provider adapters.

Use Material for MkDocs to turn Markdown documentation into a searchable, navigable static site with project-ready configuration and previews.

Use Xero MCP Server to give approved MCP clients controlled access to Xero accounting data, reports, invoices, contacts, and related business records.

Use OpenRAG's built-in MCP endpoint so agents can ingest documents, search a knowledge base, create filters, and run RAG-backed chat against a deployed OpenRAG instance.

Let an agent drive a real logged-in Chrome profile through MCP for authenticated browsing, parallel tab work, and token-efficient page interaction without re-authenticating each run.

Use OCRFlux when agents need local PDF or image parsing into Markdown/JSONL with layout-aware OCR, table handling, and cross-page paragraph or table merging.

Run Codex, Claude Code, OpenCode, Pi, and similar coding agents side by side in isolated worktrees, then compare, annotate, and merge the best result.

Use MetaGPT to turn a product requirement into coordinated product, architecture, project, and engineering agent outputs that an operator can review and iterate.

Use Moltworker to deploy a supervised OpenClaw personal agent stack on Cloudflare Workers, Sandbox containers, Access, R2, and optional AI Gateway.

Use Loop Engineering to scaffold, audit, and operate repeatable coding-agent loops with explicit state, budget, readiness, and tool-specific patterns.