Agents
continued working on @activegraphai reference packs last weekend, resulted in needing to harden the runtime: it already could... - keep a co…
continued working on @activegraphai reference packs last weekend, resulted in needing to harden the runtime: it already could... - keep a complete history of everything an agent did - replay that hist
continued working on @activegraphai reference packs last weekend, resulted in needing to harden the runtime: it already could... - keep a complete history of everything an agent did - replay that history - fork into alternate timelines to try different ideas it can now... - realize it's missing a capability - write new code to add that capability - test it in an isolated copy of itself - ask a human to approve it - safely adopt it - continue running with the new capability https://activegraph.ai/blog/activegraph-1-2-to-1-7-1
Related
- a parallel experiment building a coding agent on top of @activegraphai. you can see everything flattened down to a single event log trace
- ActiveGraph makes the agent trace the runtime: Yohei Nakajima's open-source Python runtime treats an append-only event log as the source of …
- the log is the agent!
- here's an activegraph based deep research agent that gives you full graph/trace of claims, sources, agent activity...
Source: Yohei Nakajima (X) | 2026-07-14