Inference Optimization Engineer

Hedra's MCP and CLI: Bring Hedra inference into your own agents. Avia Haimovich · August 31, 2026 Hedra is an inference and research company building the infrastructure for visual intelligence. Its goal is to make ubiquitous visual intelligence possible. As part of that, Hedra Inc. is expanding its product surface with the Hedra CLI and MCP, built for bringing Hedra into your own agents and your own automations. Whatever you already use to get work done, ChatGPT, Claude Code, Cursor, Codex, Hermes, or Pi, can now reach Hedra's full inference library directly: accelerated open-source and third-party image and video models, with large language models coming soon, all served on its own accelerated inference stack. You don't need to open Hedra to generate with Hedra, ask the agent you're already talking to, and the CLI or MCP handles it, saved to your Hedra library through MCP, or as a file you download through the CLI. Agents have already made teams more productive everywhere else. This brings that same leverage to visual inference. Automate entire functions, generate personalized sales videos and demo content on the fly, or hand your whole ad and marketing pipeline to an autonomous agent built on Hedra. Your team's agent already knows how to do this. Most teams don't need to be sold on using Claude or ChatGPT anymore, that call's already been made. What's still clunky is everything downstream of it: someone needs an image or a video, so they close the chat, open a different tab, and go make it somewhere else. MCP closes that gap. Connect Hedra once, and generating a visual becomes one more thing the agent your team already runs everything through can do, not a reason to leave it. For an enterprise team, that matters more than it sounds like it should. Rolling out a new tool to a hundred people means procurement, a training session, another login to manage. Rolling out an MCP connector to a team already on Claude or ChatGPT is closer to flipping a switch: everyone who already has agent access now has Hedra access, without anyone individually deciding to adopt something new. What is an MCP server? MCP stands for Model Context Protocol. It's a standard that lets an agent like Claude or ChatGPT connect to outside tools and use them directly, inside the same conversation, instead of just answering questions about them. Hedra publishes an MCP server so an agent can generate images and video the same way it already reads a file or searches the web, one more tool it has access to. What is a CLI? CLI stands for command-line interface, a program you or an agent runs directly in a terminal instead of through a chat window. Hedra's CLI works like any other command-line tool: install it, sign in, and run a command like hedra-cli queue submit to generate something and get a file back. MCP or CLI? Both are legitimate ways to generate with Hedra, and most people end up reaching for each one at different times, depending on what they're doing and what's their workflow. | / | MCP | CLI | | Where the output goes | Saved to your Hedra library, plus a link to the file | A link to download the file, nothing saved to your library | | Setup | Connect it like any other MCP server, no install | Install via npm, Homebrew, or a script | | Billing | Credits, or pay-as-you-go with autobilling | Credits, or pay-as-you-go with autobilling | What you can build. * Keep the context you already built. Brainstorm an idea with Claude, and by the time you're ready for a visual, the conversation already holds the whole thing: the direction, the references, why you talked yourself out of the first two versions. Copy all of that into Hedra's canvas and you're starting over. Ask for the visual right there instead, and it generates from everything you already said, not a prompt you have to reconstruct from memory. * Bring in the design files you already have. If Figma's MCP, or whatever else your team runs, is connected to the same agent, that context travels with it. Ask for a visual that matches an existing brand file, and the agent already has it, instead of you exporting it and re-uploading it somewhere else. * Swap a visual without leaving the chat. Ask Claude to change the hero image on your homepage, and get back the new version, no design queue, no separate tab. * Turn a site refresh into one script. Point the CLI at every image on your site and regenerate the batch overnight, instead of opening a canvas hundreds of times. * Keep your company's channel stocked without booking a shoot. Point the same agent that already runs your content calendar at Hedra, and a new video becomes one more thing it generates on schedule. * Generate a personalized sales video on demand. Demo content and sales videos become something your agent can produce on the fly, instead of a separate production request to someone else's queue. * Let the pipeline run itself. Hand your ad and marketing pipeline to an agent that already plans it, generation included, instead of handing visuals off as a separate step. Getting started. Pick whichever fits how you work. Using the CLI: * Install it, npm install -global @hedra/cli, Homebrew (brew install hedra-labs/tap/hedra-cli), or the installer script at hedra.com/develop. Source is on GitHub if you'd rather build it yourself. * Sign in, two ways to do it: * With a key: grab an API key from your Hedra account and set it as HEDRA_API_KEY. * Without a key: run hedra-cli auth login and authenticate in the browser instead. No subscription needed either way. * Run a command yourself, or point a coding agent at it: hedra-cli jobs submit -model minimax-h3 -input '{"prompt": "a fox sprinting across fresh snow"}'. Using MCP: * Connect it the same way you'd add any other MCP server to Claude or ChatGPT. Full setup steps live at hedra.com/mcp. Either way, pay with your existing credits or set up pay-as-you-go with autobilling, no subscription required. Try it. You already have an agent, it just didn't have Hedra yet. Connect the MCP at hedra.com/mcp, or install the CLI at hedra.com/develop, whichever fits how you work. The next image or video you need is one message away, not a separate tool to open. Faq. Do I need a Hedra account to use the CLI or MCP? Yes, either way, but it's free, no subscription needed. MCP works inside the account you already have. The CLI just needs you signed in too, even though it doesn't save anything back into your library. Do I need to set this up separately for everyone on my team? No, if your team already rolls out Claude or ChatGPT centrally, Hedra's MCP works the same way. Connect it once at the workspace level, and everyone with existing agent access has Hedra access too, nobody sets up their own separate connection. Does my CLI generation show up in my Hedra account? No. You get a link to download the file. MCP generations land in your library automatically; CLI ones don't. Is this the same as Hedra's API? Not exactly. The API and SDKs are for building your own product on top of Hedra's models, for other people to use. MCP and CLI are for reaching your own account, or getting a file back, through an agent you already use, not for building something separate. Which models can I reach through this? The same library the API serves: MiniMax H3, Veo, Nano Banana, Seedance 2.5, and the rest of its accelerated image and video catalog, plus its own in-house models. Large language models are coming soon. Anything Hedra Inc. serve, your agent can reach. Which agents work with this? Claude, ChatGPT, Cursor, Claude Code, Codex, Hermes, and Pi are all confirmed to work, through whichever surface fits how you're working. Do I need a subscription? No. Pay with your existing credits, or set up pay-as-you-go with autobilling.

Hedra Omnia release shows why AI video is moving beyond talking heads. The race to make AI video feel genuinely human just took a meaningful turn. Hedra has released Omnia, a new video model designed to solve a problem creators have been quietly complaining about for years: AI video that looks sharp but feels dead. Omnia's debut matters because it challenges a long-standing tradeoff in generative video - choose expressive, voice-driven avatars or cinematic visuals, but rarely both at the same time. A long-standing split in AI video finally gets addressed. Until now, the AI video market has been divided into two camps. On one side are "talking head" systems. They do voice well, but everything else is frozen: static cameras, stiff bodies, environments that feel like wallpaper. On the other are general video generators that create dynamic scenes but treat audio as an accessory rather than a driver of performance. The result is visually impressive clips that fall apart the moment someone speaks for more than a few seconds. Omnia was built to close that gap. Instead of stitching together separate systems for visuals, motion, and sound, Hedra engineered a single model that reasons over all three at once. The idea is simple but ambitious: if speech, movement, and camera behavior influence each other in real life, an AI model should treat them the same way. The technical shift behind Omnia isn't about higher resolution or flashier effects. It's about coordination. In most AI video systems, audio comes last - used mainly to sync lips. Omnia flips that priority. Speech rhythm influences body motion. Emotional tone shapes facial expressions. Timing affects how the camera moves through a scene. The model builds an understanding of the entire performance before generating the first frame. That approach shows up in details professionals notice immediately: natural blinking, subtle head movement between words, hands that stay stable, and logos that don't warp or dissolve halfway through a shot. These aren't cosmetic upgrades. They're the cues viewers subconsciously use to decide whether a video feels authentic or artificial. One notable choice Hedra made was to avoid chasing hyper-sharp realism. In practice, overly crisp faces with robotic motion tend to feel unsettling. Omnia prioritizes believable presence instead - continuous motion, micro-expressions, and camera behavior that responds to the subject rather than drifting aimlessly. Camera control becomes part of the performance. One of Omnia's more consequential features is its approach to camera direction. Instead of treating the camera as an invisible observer, the model treats it as part of the scene. Creators can specify push-ins, pull-outs, tracking shots, or orbiting movement and expect those directions to be followed consistently. More importantly, the camera stays coherent relative to the subject. If the speaker leans forward or shifts tone, the framing adjusts in ways that feel intentional rather than random. For anyone who has tried to create AI video with even modest cinematic ambition, this is a big deal. Camera motion has traditionally been one of the fastest ways to expose a clip as AI-generated. Omnia's ability to maintain spatial logic suggests a move toward AI video that can be directed, not just prompted. Where this model is likely to shine first. Omnia is optimized for short, character-driven clips - roughly eight seconds at full HD. That constraint is deliberate and revealing. The strongest early use cases are likely to be social and brand formats where authenticity matters more than spectacle. Influencer-style videos, interview snippets, podcast clips, and conversational ads all benefit from consistent voice, natural motion, and stable visual details. In those formats, even small visual glitches can break trust. Brand teams, in particular, may pay attention to Omnia's handling of logos and product elements. Generative AI has struggled with brand integrity, often rendering text or marks unusable. Reliable control over those details lowers one of the biggest barriers to AI video adoption in advertising and marketing. There's also a quieter implication for music and performance content. Because audio timing influences motion throughout the clip, rhythm-driven material - singing, spoken word, or musical dialogue - comes across as more intentional than the usual lip-synced output. Why this news matters beyond creators. For consumers, the shift is subtle but important. As AI video becomes more believable, audiences will encounter synthetic performers in contexts that previously required human production - local ads, explainer content, and social media storytelling. The line between filmed and generated video will blur further, raising new questions about disclosure and trust. For businesses, Omnia signals that AI video is moving from novelty toward workflow tool. When camera control, voice consistency, and brand reliability improve, AI video stops being experimental and starts competing with traditional production for certain use cases. And for the industry at large, the model reflects a broader trend: progress in generative AI is increasingly about coherence, not raw visual power. The models that win won't just look better frame by frame; they'll feel more intentional over time. Looking ahead: what the next year could bring. Expect more pressure on AI video platforms to integrate audio, motion, and camera logic rather than treating them as separate problems. Omnia sets a benchmark that competitors will have to respond to. There are still clear limits. Short clip lengths constrain narrative complexity, and single-subject scenes remain the safest ground. But those constraints also suggest a roadmap. As models like Omnia mature, multi-character interaction and longer scenes become more feasible. The bigger risk is complacency. As AI video becomes more convincing, misuse and over-automation become easier. Platforms will need to balance creative power with safeguards that maintain transparency and accountability. For now, Omnia represents a meaningful shift in priorities. Instead of asking how real AI video can look, Hedra is betting that the more important question is how real it can feel.