AI TaskVector - building a local multi-agent platform for automations, coding and personal use

Hugging Face user DHEIVER released a BETA version of AI TaskVector, an open-source local platform that combines an AI agent with an agent factory, offering a built-in low-code framework for automations, an agentic runtime and orchestration, and co-pilot and long-polling modes, including a Telegram bot gateway workflow example. DHEIVER said the goal is a platform where anyone can build, run and train agents without deep technical skill, and asked the community for feedback and contributions. A commenter on the post warned that orchestrating multiple agents locally creates context management challenges, noting that KV cache grows rapidly in looped conversations such as the Telegram gateway and that without pruning or summarizing intermediate states, cost per successful task cycle can spike.

Dear Huggingface community, I was kind of experimenting with different models a few month ago, which ended up with this BETA version of AI TaskVector. Currently, it is a combination of both an AI Agent and factory that runs in local: - Built-in low-code framework for automations - Agentic runtime and orchestration - Co-pilot mode and Long-polling mode e.g. run this workflow to make the Agents talk over Telegram: config/workflow examples/telegram bot gateway.json The idea was to create an open-source platform where anyone could be AI-assisted with building, running and training their agents without deep knowledge and skill involved. Anyways, these were just my thoughts looking forward, it may end up being something else, who knows… I would be more than happy to have any useful feedback, comments. Feel free to create units, roles, play around with the repo and join my journey of the exploration, since I’m still learning. DHEIVER https://discuss.huggingface.co/u/DHEIVER 2 Orchestrating multiple agents locally introduces significant context management challenges. When agents converse over a loop like your Telegram gateway, the KV cache grows rapidly, especially with long-polling. Have you implemented a strategy to prune historical turns or summarize intermediate states to keep inference latency stable? Without aggressive context window management, the cost per successful task cycle can spike faster than the model’s raw token speed suggests.