and here's what a coding agent on activegraph looks like basically you always get a trace and a graph automatically
@yoheinakajima
-
ActiveGraph deep research agent gives full trace of claims and sources
By
–
here's an activegraph based deep research agent that gives you full graph/trace of claims, sources, agent activity…
-
ActiveGraph AI runtime built around memory performs well on privacy benchmarks
By
–
even though @activegraphai is not a memory tool, it's a runtime built around memory so it can do well there cool to see a third party verify this and see that activegraph does well on privacy programs (from @harvey
's legal agent benchmark), which heavily relies on compliance -
BabyAGI diagram praised, meta path leads to ActiveGraph
By
–
yeah this 2023 babyagi diagram was on point 🙂 thx! seems like if you keep going meta, you'll end up with something like activegraph, lots of ppl seem to have been circling similar ideas
-
ActiveGraph agents coordinate via shared graph without direct agent communication
By
–
especially around the smaller workers piece at the end. activegraph agents don’t have agents that talk to each other, nor workflows, but tons of mini agents coordinating through a shared graph
-
Activegraph: log-centric agent primitive experiment aligning with ideas
By
–
I have not, and I assume you made it seamless for your users 🙂 Activegraph is an experiment in a new agent primitive (log centric vs LLM centric). very early as a concept, but aligned with a lot of the ideas in your original post so thought you might find it interesting
-
ActiveGraph agents have automatic first-class tracing, not bolted on
By
–
if you build any agent on activegraph, the trace is automatic and first-class, not bolted on
-
Parallel experiment building coding agent on ActiveGraph AI with event log trace
By
–
a parallel experiment building a coding agent on top of @activegraphai
. you can see everything flattened down to a single event log trace -
Tools should be called from code, not from within LLM API
By
–
slowly we're all realizing that tools should be called from code, not from within the llm api
