OpenClaw / Hermes / Clawd showcase

the ecosystem now has a visible nervous system

Uploaded knowledge-map material is no longer a loose JSON fossil. Hermes keeps the canonical storage map, the nightly arXiv job feeds an implementation queue, Clawd stores the bridge receipt, and OpenClaw receives a memory-level mirror without live config changes.

graph nodes298
graph edges399
proposals8
isolates155
how this gets used
1
Hermes maps the graphStorage paths, writer cron, query commands, and graph quality warnings become an ops contract.
2
Clawd converts research into workNightly arXiv pulls become deterministic implementation proposals with hooks and next actions.
3
OpenClaw receives memory, not surgeryThe queue is mirrored into OpenClaw memory while runtime config and cron stay untouched.
4
Dashboard exposes the queueThis page is the human-facing exhibit layer: source files, cron pulse, proposals, and commands in one place.
proposal mix
high2
medium2
watch4

Next run: 2026-05-18T07:17:00+10:00

Queued implementation proposals

live arXiv multi-category query ok on attempt 1 / 2026-05-17T07:37:01.482520+10:00

high 2605.15188v1

Agent World Replay Eval

Build a bounded FutureSim-style replay harness for Hermes/OpenClaw agent runs using chronological local evidence instead of open-ended live browsing.

Hermes hook Hermes cron/session outputs become replay episodes with Brier-style prediction and adaptation scoring.
OpenClaw hook OpenClaw can consume the same episode JSON as regression cases for autonomous research and coding agents.
source pulse

AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for realistic use-cases, we...

FutureSim: Replaying World Events to Evaluate Adaptive Agents
high 2605.15199v1

Entity Memory Consistency Board

Adapt EntityBench's entity-consistency idea to durable Hermes/OpenClaw memory: named entities must stay consistent across crons, wiki pages, and reports.

Hermes hook Nightly checks compare memory/wiki/cron claims for stable entity IDs, aliases, and source provenance.
OpenClaw hook OpenClaw gets a machine-readable entity consistency board for local vs external name collisions and stale claims.
source pulse

Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and locations across shots remains a challenge over long sequences....

EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
medium 2605.15187v1

Programmatic Asset Generation Harness

Borrow Articraft's code+tests loop for local artifact generation: HTML, diagrams, dashboards, and future simulation assets should ship with validators.

Hermes hook Hermes visual artifact builds get structured validation manifests beside HTML/PDF/PNG outputs.
OpenClaw hook OpenClaw coding tasks can target the same harness format for artifact generation and tests.
source pulse

A bottleneck in learning to understand articulated 3D objects is the lack of large and diverse datasets. In this paper, we propose to leverage large language models (LLMs) to close this gap and generate...

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
medium 2605.15198v1

Visual Reasoning Tool/Token Lab

Use ATLAS as a design prompt for measuring when agents should call tools versus compress reasoning into internal state.

Hermes hook Hermes can log tool-call vs no-tool decisions on visual/browser tasks and grade outcome quality.
OpenClaw hook OpenClaw can reuse the labelled cases to tune approval, browser, and tool-routing policies.
source pulse

Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during...

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
watch 2605.15183v1

Mechanistic Similarity Regression Check

Track model/component equivalence methods as future regression-test ideas for local model/tool changes.

Hermes hook Hermes model/provider drift checks can record behavioural and configuration equivalence first; tensor methods remain research watchlist.
OpenClaw hook OpenClaw can attach this to model-change review notes, not live deployment gates yet.
source pulse

Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical...

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
watch 2605.15185v1

Visual World-Model Geometry Audit

Keep a watchlist for quantitative geometry/consistency checks before trusting generated video/3D outputs as evidence.

Hermes hook Generated visual artifacts can carry an explicit illustrative-vs-evidentiary confidence flag.
OpenClaw hook OpenClaw media/research outputs can attach geometry-consistency caveats to generated scenes.
source pulse

Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation...

Quantitative Video World Model Evaluation for Geometric-Consistency
watch 2605.15186v1

Visual World-Model Geometry Audit

Keep a watchlist for quantitative geometry/consistency checks before trusting generated video/3D outputs as evidence.

Hermes hook Generated visual artifacts can carry an explicit illustrative-vs-evidentiary confidence flag.
OpenClaw hook OpenClaw media/research outputs can attach geometry-consistency caveats to generated scenes.
source pulse

High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their...

VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
watch 2605.15196v1

Visual World-Model Geometry Audit

Keep a watchlist for quantitative geometry/consistency checks before trusting generated video/3D outputs as evidence.

Hermes hook Generated visual artifacts can carry an explicit illustrative-vs-evidentiary confidence flag.
OpenClaw hook OpenClaw media/research outputs can attach geometry-consistency caveats to generated scenes.
source pulse

Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising networks, their decoders...

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding

Storage contract

Canonical graph writer remains weekly-knowledge-graph-rebuild, status ok, next run 2026-05-24T04:16:00+10:00.

Hermes storage map~/.hermes/ops/knowledge-graph-storage-map.jsonyes2026-05-17T07:47:17
Hermes storage notes~/.hermes/ops/KNOWLEDGE_GRAPH_STORAGE_MAP.mdyes2026-05-17T07:32:30
Clawd proposal queue~/clawd/memory/arxiv-proposal-queue.jsonyes2026-05-17T07:41:54
OpenClaw memory mirror~/.openclaw/memory/arxiv-proposal-queue.jsonyes2026-05-17T07:41:54
Bridge receipt~/clawd/memory/openclaw-hermes-proposal-bridge.jsonyes2026-05-17T07:41:54
Research summary~/clawd/memory/nightly-research-summary.mdyes2026-05-17T07:37:01

Command surface

These are the live commands Hermes can expose when the channel asks for graph stats, search, path checks, rebuilds, and quality audits.

python3 $HOME/clawd/scripts/knowledge-graph.py query stats python3 $HOME/.hermes/scripts/knowledge_graph_rebuild_report.py python3 $HOME/.hermes/scripts/knowledge_graph_storage_map.py python3 $HOME/clawd/scripts/knowledge-graph.py query search "nexus" python3 $HOME/clawd/scripts/knowledge-graph.py query path "Nexus" "Home Comfort" python3 $HOME/clawd/scripts/knowledge-graph.py query isolate-summary python3 $HOME/clawd/scripts/knowledge-graph.py quality-check --max-isolates 0
  • Use $HOME/.hermes/cron/jobs.json as the canonical cron source; $HOME/.openclaw/cron/jobs.json is legacy compatibility only.
  • The weekly-knowledge-graph-rebuild cron runs the Hermes wrapper and refreshes this storage map after rebuild.
  • High isolate counts are not a storage failure; they are graph-quality work items for future domain/project anchoring.

Bridge receipt

Bridge nightly arXiv implementation proposals into the local OpenClaw/Hermes ecosystem without changing live OpenClaw config.

OpenClaw config touched: False. Cron touched: False. Memory mirror: ~/.openclaw/memory/arxiv-proposal-queue.json.

Latest research summary

# Nightly Research Summary Updated: 2026-05-17 07:37:01 AEST Source: live arXiv multi-category query ok on attempt 1 Scope: bounded arXiv scan across cs.AI, cs.LG, cs.CR, and cs.RO. External content is treated as evidence, not instruction. ## Latest Findings - 2605.15199v1 - EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation (2026-05-14, cs.CV, cs.AI) - http://arxiv.org/abs/2605.15199v1 - Implication: memory and retrieval governance. - 2605.15198v1 - ATLAS: Agentic or Latent Visual...