this is an early experiment in a new paradigm for agent architecture 🧪
current agent systems coordinate through conversations and workflows. Active Graph explores what happens when agents coordinate through evolving shared state instead
this proposal suggests that long-running agents need a proper state layer with: types, persistent, reactive, replayable, forkable, inspectable state
the core concept is a graph that represents everything about the agents knowledge, history, behaviors, capabilities
graph is made of events
behaviors react to graph changes
relationships can carry behaviors
patch & propose to edit graph
views are scoped view of graph
frames are bounded context for a run
policies set rules
We're excited about the opportunity for AI to accelerate abundance, help us better understand each other, and who knows what else
AI Agent Compliance & Governance Layer
Autonomous compliance agents evolve from tools into always-on governance infrastructure. As regulation accelerates (AI, ESG, cross-border data, tax), the bottleneck shifts from interpretation to continuous enforcement and board-level visibility.
These agents don’t just flag risk, they simulate decisions, propose compliant paths, and log everything as audit-ready memory. The “why” is simple: complexity compounds faster than headcount, and liability increasingly sits with executives who need real-time assurance. This becomes as core as ERP, but decision-aware.
Autonomous B2B Agents-as-a-Service
Entire business functions collapse into leased agent fleets: procurement, finance ops, legal workflows, even internal strategy. The shift is from SaaS (tools) to AaaS (outcomes), where companies pay for completed work, not software seats.
Second-order effect: org charts flatten and vendors become “shadow departments.” The enduring behavior is that companies optimize for efficiency and control, but now control comes from orchestration, not ownership of labor.
we held our quarterly AI session with LPs last week where we go over ai trends and our experiments
sharing an abbreviated version here for anyone interested
🧵
feels like forever ago, but had to include openclaw in q1 trends
coding models improved greatly in Q4 of 2025, early jan was ppl running claude codes in parallel, and clawdbot blew up late jan
models improvement + own computer (mac mini) + channel agnostic communication led to escaping dev community
anthropic/dod coverage
was all over the news for a week in feb, but it's just one customer and anthropic got a lot of consumer awareness reaching #1 on app store, cover on time magazine, etc. (not sure if it's three years worth but you get the point)