Agents that think,
decide, and act.
We build autonomous AI agents that operate in live environments with real constraints, real people, and real consequences — running on local inference, not cloud APIs.
Talk to the research team →Autonomous agent architectures.
Tool-use agents that plan multi-step work, use real tools to execute, monitor their own progress, and recover from failure without human intervention. Planner → researcher → executor → critic loops, with persistent state and traceable reasoning.
Constitutional guardrails.
Hard-coded behavioral invariants that constrain what an agent can and cannot do — checked at every action, not just at prompt-time. We study how policy kernels survive adversarial environments and long-horizon autonomy.
Emotional & behavioral modeling.
How agents represent affect, frustration, urgency, and trust — and how those internal states change their decisions over time. We're interested in agents that have something like a temperament, not just a temperature parameter.
Local-first inference on Apple silicon.
The agents we ship run on hardware our clients control. MLX, llama.cpp, and custom runtimes targeting M-series GPUs — no cloud round-trips, no data leaving the building, no per-token bills. Inference latency in milliseconds, not seconds.
Working on hard problems?
We collaborate with researchers, partners, and teams who want autonomy that actually ships. Drop us a line.
services@blackdagger.ai