> activegraph / blog

Notes from the active graph.

Announcements, deep-dives, and research from the team building activegraph. RSS at /blog/rss.xml.

Log · 18 entriesNewest first

2026-07-09
Pokemon TCG AI Battle - Things we tried that didn't workexternal
I played the card game over 20 years ago, and these days play with AI a lot. I took a stab at this tournament without relearning the game to see how far AI could take me. The short version: some things I tried improved weak deck/agent scores a bit, but the best scores came from copying strong public examples from the forum, and I couldn't meaningfully improve them. The write-up documents what moved, what failed, and what I would not spend games on again — the constraints (5 submissions/day, ~24hr score settling, incomplete offline opponents, stochastic outcomes, Kaggle runtime drift) shape most of the lessons.
2026-07-08
ActiveGraph 1.2.0 to 1.7.1: hardening the reference packs pulled the runtime forward
A coordinated push across two repos: the reference packs got hardened for autonomous-agent use, and the activegraph runtime shipped seven releases in a day to support them. The through-line is one loop — fork, trial in a child process, owner approval against pinned bytes, quiescent promote, watch window — recorded end-to-end in the event log.
2026-07-04
Five Numbers and a Negative Resultexternal
Part 1 of a series on benchmarking activegraph as the memory substrate for a terminal agent. activegraph works as a harness (competitive with terminus control), but naive graph retrieval lost to the prompt-cached transcript baseline. The interesting signal is in the shape of the failures.
2026-07-03
Active Graph v1.2.0: The Graph Projection Becomes Pluggable
v1.2.0 makes the materialized graph a pluggable seam with FalkorDB as the first external backend — native edges, Cypher query push-down, a conformance suite for future backends — plus a CI gate for the full test suite and one license everywhere.
2026-06-18
ActiveGraph Packs: A Composable Assistant Substrate
A reference pack library for graph-native assistants — memory, identity, tools, comms, and domain capabilities composing through evented state instead of a central orchestrator.
2026-06-13
I Built a Research Agent That Shows Its Work
A graph-native, event-driven deep research agent that exposes its reasoning, evidence, and dead ends instead of flattening them into prose. Open source, live demo.
2026-06-13
Building Deep Research on ActiveGraph: A Field Report
A first-person field report on building ActiveGraph Deep Research — the mental shifts, the bugs that taught me the runtime, and the design decisions I'd defend.
2026-06-10
Active Graph v1.1.0: Better Runtime Resilience, Better Operator Tools
v1.1.0 tightens the surfaces that matter once an agentic system leaves the demo stage: bounded LLM retries with audit, CLI inspect tools, fork-time pack overrides, OpenTelemetry metrics, OpenAI tool-call parity, and stricter docs and release gates.
2026-06-10
Regimes: An Auditable, Held-Out Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraphexternal
Paper #2 follows up on paper #1's open question — ActiveGraph as an architectural affordance for self-improving agents. A reproducible gated self-improvement loop with modest autonomous gains on LongMemEval, plus a regime-to-seam approach where categorized failures fix targeted areas behind a binding held-out gate. Discussion: https://x.com/yoheinakajima/status/2064830891143381076
2026-06-08
AG Coder: A Reference Coding Agent Built on ActiveGraph
An open-source coding agent built on ActiveGraph: graph-native, event-sourced, and auditable by default. A reference for what a coding agent looks like when the runtime is the substrate, not a wrapper around an LLM loop.
2026-06-05
Introducing learn.activegraph.ai
A new site for activegraph that teaches the framework as a refactor: start from the while-loop agent everyone has built, substitute one piece at a time, and end up at an event-sourced graph runtime with replay, provenance, contradictions, and forkable conclusions.
2026-06-02
Code Without Authority
An authority lifecycle for generated behavior in an event-sourced agent runtime
2026-06-01
Compile From the Log, Don't Replace It
Hybrid Semantic Memory on LongMemEval-S: Retrieval Significance, Reader Bottlenecks, and the Case for Provenance-Backed Facts
2026-06-01
Self-Modification Is Not Binary
Typed, auditable self-change on an event-sourced agent runtime
2026-05-30
What Semantic Memory Forgets: ActiveGraph on LongMemEval-S
Debugging ActiveGraph on LongMemEval-S: LLM extraction moved the semantic-memory pack from 60.6% to 83.4%, role-aware assistant retention fixed a 75.0% → 98.2% assistant-memory failure class, and the remaining errors showed why semantic memory should compile back to source evidence.
2026-05-25
Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S
Technical benchmark note: 85.6% QA accuracy and 86.2% turn answer-in-context at 2,462 mean context tokens, with deterministic non-generative ingestion.
2026-05-21
The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systemsexternal
Append-only event log as source of truth, working graph as deterministic projection, behaviors react and emit, yields deterministic replay + cheap forking + end-to-end lineage. Discussion: https://x.com/yoheinakajima/status/2057812713045377055
2026-05-20
activegraph: agents that coordinate through replayable stateexternal
v1.0 is out: a Python runtime where long-running agents share a reactive, event-sourced graph as their world — fork, replay, and audit included.

Notes from the active graph.

Pokemon TCG AI Battle - Things we tried that didn't workexternal

ActiveGraph 1.2.0 to 1.7.1: hardening the reference packs pulled the runtime forward

Five Numbers and a Negative Resultexternal

Active Graph v1.2.0: The Graph Projection Becomes Pluggable

ActiveGraph Packs: A Composable Assistant Substrate

I Built a Research Agent That Shows Its Work

Building Deep Research on ActiveGraph: A Field Report

Active Graph v1.1.0: Better Runtime Resilience, Better Operator Tools

Regimes: An Auditable, Held-Out Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraphexternal

AG Coder: A Reference Coding Agent Built on ActiveGraph

Introducing learn.activegraph.ai

Code Without Authority

Compile From the Log, Don't Replace It

Self-Modification Is Not Binary

What Semantic Memory Forgets: ActiveGraph on LongMemEval-S

Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S

The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systemsexternal

activegraph: agents that coordinate through replayable stateexternal