Video & Animation

Move big photo libraries, takeouts, and nested albums into Immich with metadata intact instead of babysitting one-off uploads.

Run local Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3, and other SaaS API emulators over a controlled corpus so agents and integrations can be tested without vendor accounts, OAuth, secrets, or network calls.

Implements Camelot library for advanced PDF table detection using lattice and stream parsing algorithms. Processes complex multi-page documents with OpenCV-based edge detection and outputs normalized DataFrames with cell-level confidence scores.

Analyzes Buildkite pipeline YAML and optimizes parallelism using the Buildkite REST API v2 and GraphQL API. Reduces build times by identifying bottleneck steps and suggesting agent queue rebalancing.

Use RAGFlow to ingest complex documents, build governed RAG knowledge bases, and give agents higher-fidelity context for retrieval-augmented workflows.

Ingest documents into Morphik, expose retrieval over AI-app knowledge, and tune document search quality before handing context to agents or RAG workflows.

Adapt, review, schedule, and publish approved social content across multiple platforms through the BulkPublish API and hosted MCP.

Leverages Bun

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

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

Give Claude Code a routed skill pack for designing, validating, debugging, and deploying n8n workflows through n8n-mcp.

Convert a bounded document set into a Neo4j knowledge graph, inspect extracted nodes and relationships, and use it for graph-backed RAG.

Model Go-native agent systems with graph workflows, tool calls, memory, MCP, A2A, evaluation, and OpenTelemetry observability.

Record AI coding sessions next to commits so an agent can recover why code changed, resume from checkpoints, and hand off work cleanly.

Use Letta to create agents whose identity, tools, memory blocks, and conversation state persist across sessions for long-running assistant or application workflows.

Compose coding-agent primitives in Rust, including tool execution, LLM streaming, sub-agent orchestration, memory, and MCP support, as an embeddable application workflow.

Creates dynamic Buildkite pipelines using the Buildkite REST API and pipeline upload mechanism. Implements conditional step generation based on file change detection via git diff.

Watch live Linux and container activity through eBPF so you can triage suspicious runtime behavior before it disappears into guesswork.

Turn a live webpage into a clean offline artifact such as a PDF or readable archive for review, citation, or handoff.

Ingest disk, log, and system artifacts into a sortable forensic timeline before analysis, scoping, or case review.

broot is a Rust-based terminal tool that provides a new way to see and navigate directory trees. It offers fuzzy search, file preview, git status integration, and an interactive tree view that adapts to your terminal size.

Expose browser-use web automation through an MCP server so Cursor or another MCP client can operate websites with browser state returned to the agent.

Index local coding-agent sessions into a searchable SQLite-backed view so you can inspect usage, compare failures, and recover prior context quickly.

Records and replays browser sessions using rrweb recording library with DOM mutation serialization. Integrates with LogRocket API and FullStory Data Export API for session analytics.