Most agent demos stop at the model call. I build what's around it — orchestration, tool servers, retries, evaluation — the part that decides whether it survives contact with production.
Agent infrastructure MCP servers and orchestration frameworks that give LLMs real tools — LangGraph pipelines, Claude Code integrations, multi-step research and generation systems. | Applied AI products End-to-end tools people actually use — video object removal and inpainting, presentation generation, asset discovery, content and media pipelines, voice and video automation. | Fundamentals Comfortable below the framework line — implementing the underlying math by hand instead of only calling an API. |
01video-object-remover — Click an object in a video and get back either a matte that tracks it or the plate with it removed. SAM 2 tracks the object across the clip, ProPainter reconstructs the background behind it; the track is cached by prompt, so pulling a matte and then removing the same object pays for tracking once. Ships as a desktop app, a local web app, and a CLI.
PythonSAM 2ProPainterPyTorchFFmpeg
02propainter-delogo — Removes a static logo or watermark and rebuilds what was behind it, instead of smearing pixels over it like ffmpeg delogo. Windowed and shot-aware, so only a crop around the logo is inpainted and composited back at native resolution — every other pixel is byte-for-byte the source. 4K-friendly, audio preserved.
PythonProPainterOpenCVFFmpegCUDA / MPS
03clipping-mcp — MCP server that gives Claude Code 41 tools to edit video and audio, on FFmpeg + ElevenLabs: trimming, multicam podcast editing, AI voiceover, timeline projects rendered through Remotion.
PythonFFmpegMCPElevenLabsRemotion
04Deep Research Framework — Plugin-based multi-agent research system on LangGraph. Decomposes a query, retrieves from multiple sources, reflects on what's missing, and synthesizes a cited report, with automatic tool fallback and complexity-based model routing.
PythonLangGraphMulti-agent orchestration
05NanoBanana Shot Division — Cinematic shot-division workflow for Claude Code. Takes a creative brief, plans an adaptive DAG, and generates continuity-consistent multi-shot storyboards on fal.ai's image models.
PythonClaude Codefal.ai
06Reel Asset Engine — AI asset search engine that aggregates images, video, and articles from SearxNG, Pinterest, Unsplash, Freepik, and Pexels, then uses LLMs to score and summarize what it finds.
Next.jsTypeScriptLLM scoring
07PPT Maker — Turns a prompt into a structured, styled deck in seconds — nine layout variants, tone and purpose controls, built on GPT-4.
Next.jsTypeScriptOpenAITailwind
08Project Companion — Project management that runs with your coding agent: a PRD, a Kanban board, and a git tree that proves what was actually built, all stored in one .project file the agent can read and update directly through a bundled MCP server.
Next.jsTypeScriptMCPReact FlowLiveblocks
09Context Graph Engine — Context store for agentic systems: what an agent knew, decided, and derived, kept on a tamper-evident record that can still forget something on request — a scoped purge that removes the data while the verification chain stays unbroken.
TypeScriptBunMCPTamper-evident logs
Building agent infrastructure and shipping applied AI products as co-founder at Boring People. Interested in tool-use, multi-agent orchestration, and the unglamorous plumbing that makes an agent reliable in production.
mailsubhapattnaik@theboringpeople.ininin.linkedin.com/in/subha-pattnaik-929488222