Dr. Farshid Pirahansiah
AI & Computer Vision Engineer • pirahansiah.com
• 10,000+ papers/year per field (ArXiv overload).
• Manual literature synthesis & BibTeX management.
• Broken code repos, missing dependencies, failed builds.
• Passive LLM chats lose context and cannot touch local files/tools.
• Autonomous tool calling: Terminal, ArXiv, Python, Web extraction.
• Persistent Memory & reusable Skill System.
• Parallel subagents (`delegate_task`) for concurrent sweeps.
• Runs on Local LLMs (oMLX/llama.cpp) & Cloud Providers.
A unified terminal & GUI agent that acts as a full-time research assistant.
8 new research skills installed + 8 existing — full toolkit for literature sweeps, critique & synthesis.
| Skill | Trigger / what it does | Status |
|---|---|---|
deepdive | Deep multi-source investigation; cited synthesis with confidence + disagreement mapping | NEW |
researchgap | Finds gaps, contradictions & open problems in a topic's literature; proposes research questions | NEW |
critic | Rigorous critique of a paper/claim/argument with severity-rated weaknesses + verdict | NEW |
literature-review | Themed survey of a topic with annotated bibliography | NEW |
synthesise | Merges several sources into one attributed synthesis; flags consensus vs open questions | NEW |
factcheck | Verifies claims against sources; labels each supported/contradicted/unverifiable | NEW |
question-storm | Generates diverse, prioritized research questions across levels | NEW |
cite | Formats references in a citation style (APA/MLA/IEEE/BibTeX); finds real sources | NEW |
arxiv | Search arXiv papers by keyword/author/category | existing |
llm-wiki | Build/query interlinked markdown knowledge base | existing |
grounded-citations | Ground answers in cited verifiable sources | existing |
reference-curation | Audit/curate doc reference links | existing |
polymarket | Query Polymarket markets/prices | existing |
competitor-news-monitor | Watch companies for material news | existing |
blogwatcher | Monitor blogs/RSS feeds | existing |
research-paper-writing | Authoring structure for research papers | existing |
Procedural Memory
ArXiv, LaTeX, W&B, PyTorch, Git workflows.
Durable Profile
User bio, SSH nodes, GPU clusters, research domain.
Parallel Workers
`delegate_task` for parallel experiments & sweeps.
Multi-Surface
CLI, Desktop GUI, Web Dashboard, Telegram, Discord.
Supports 35+ providers: Local oMLX, vLLM, OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter.
# 1. Official Hermes Shell Installer (uv + python venv + launcher) curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash # 2. Interactive setup wizard (Pick provider: Local LLM, Gemini, OpenAI, etc.) hermes setup # 3. Check environment health & dependencies hermes doctor # 4. Launch Hermes interactive CLI or Desktop GUI hermes # Terminal REPL hermes desktop # Native Electron GUI
Configuring ~/.hermes/config.yaml for Research Labs
model: default: Qwen3.5-4B-OptiQ-4bit # Fast local model for baseline task provider: custom base_url: "http://127.0.0.1:8000/v1" # oMLX / llama-server local endpoint aliases: reasoning: gemini/gemini-2.0-flash-lite deep-coder: deepseek/deepseek-coder agent: max_turns: 30 context_compression: true # Preserves state on huge paper reads terminal: backend: local workdir: "/Users/farshid/research-projects"
• arxiv — Direct paper search & downloading.
• grounded-citations — Verified source grounding.
• llm-wiki — Karpathy-style Markdown Knowledge Base.
• jupyter-live-kernel — Live Python kernel.
• evaluating-llms-harness — Benchmark suites.
• systematic-debugging — 4-phase root cause analysis.
• docx / pdf — Parse & edit research papers.
• architecture-diagram — Dark-theme SVG diagrams.
• markdown-to-pdf — Export clean PDF preprints.
Command: "Find recent papers on 3D SLAM and build a literature matrix"
# Hermes executes ArXiv search -> parses PDFs -> builds references matrix from hermes_tools import web_search, read_file, write_file # 1. Search ArXiv by domain & topic results = arxiv_search(query="cat:cs.CV AND title:SLAM", max_results=10) # 2. Extract key contributions, equations, and benchmarks matrix = [] for paper in results: pdf_text = web_extract(urls=[paper['pdf_url']]) summary = extract_key_innovations(pdf_text) matrix.append({"title": paper['title'], "bibtex": paper['bib'], "notes": summary}) # 3. Output clean Markdown matrix + references.bib write_file("literature_review.md", format_matrix(matrix)) write_file("references.bib", format_bibtex(matrix))
1. Clone GitHub Repo: Autonomous git checkout.
2. Inspect & Resolve Deps: Reads requirements.txt / environment.yml.
3. Fix Runtime Errors: Applies systematic-debugging to fix PyTorch CUDA mismatches or API changes.
4. Log Metrics: Generates W&B or TensorBoard plots.
Generates structured IEEE/ACM template with Abstract, Introduction, Methodology, Experiments, Related Work.
Uses grounded-citations to ensure every claim in the text links to a real ArXiv/DOI paper in references.bib.
Produces publication-ready SVG architecture diagrams, flowcharts, or Manim mathematical animations.
Zero hallucinated citations: claims are mechanically verified against PDF extractions.
Spawning Concurrent Subagents for Heavy Academic Workloads
# Main Hermes Agent dispatches 3 subagents in parallel delegate_task(tasks=[ { "goal": "Search ArXiv for 2025-2026 Vision-Language-Action models and extract benchmarks", "context": "Focus on robotics manipulation" }, { "goal": "Benchmark Qwen3.5 vs K2-Horizon on local M3 GPU using llama.cpp", "context": "Log tokens/sec, memory usage, and context latency" }, { "goal": "Format collected findings into an IEEE LaTeX draft", "context": "Save to ~/paper_draft/main.tex" } ])
memory)Stores facts that survive across every terminal session:
• Primary research focus (e.g. Computer Vision, 3D Reconstruction).
• Lab GPU Cluster details (e.g. SLURM partition a100-80gb, node IPs).
• Preferred paper format & writing style guidelines.
skill_manage)Teaches Hermes specialized lab procedures:
• Slurm Job Submission: sbatch script creation & queue monitoring.
• HuggingFace Dataset Uploads: Automated push of custom datasets.
• Lab Calibration Pipeline: Multi-camera camera intrinsic sweeps.
Local oMLX / Ollama
100% private, zero cost, runs on Mac/Linux.
Prompt Caching
Free cache hits on long paper context blocks.
Codebase Memory
Graph queries replace reading full repos.
Speedup
Parallel subagent sweeps vs manual searching.
Local models handle draft tasks & code execution; Cloud models handle complex reasoning.
Build an end-to-end multi-camera 3D point cloud generation pipeline and publish open source benchmarks on pirahansiah.com.
Hermes Execution:
• Pulled 15 camera calibration papers from ArXiv.
• Debugged OpenCV / GStreamer C++ DMA pipeline.
• Generated benchmark tables and SVG pipeline diagrams.
✓ 3d-vision.md documentation page on website.
✓ Verified OpenCV C++ code with zero memory leaks.
✓ BibTeX reference database with 15 verified citations.
✓ Interactive web visualizer demo.
✔ Autonomous Research Agent: Move from passive chatting to active tool execution.
✔ End-to-End Workflow: Literature review → Code reproduction → Experimentation → Paper drafting.
✔ Lab Privacy & Local Serving: Run on local oMLX / llama.cpp or Cloud APIs seamlessly.
✔ Parallel Power: Use subagents (`delegate_task`) for concurrent paper sweeps.
Explore the Knowledge Base & Code: pirahansiah.com
Draft bottom-up: build the evidence first, then frame it. Read top-down.
Hermes: researchgap scopes the gap · critic stress-tests claims · cite formats refs · research-paper-writing structures the draft.
Text-to-figure AI for researchers — publication-ready diagrams & charts from a description.
• Methodology diagrams — model architectures, algorithm flows, encoders, system pipelines.
• Statistical plots — generates executable Matplotlib code from raw data (no numeric hallucination).
• Aesthetic enhancement — turns hand sketches / whiteboard notes into top-venue art.
• Styles — Transformer, GAN, RAG, Multi-Agent templates; posters & more.
• 5-agent closed loop (Planner → Visualizer → …) for faithful, precise, polished figures.
• Planner turns text into structured visual layouts.
• Visualizer renders via Nano-Banana-Pro — exact shapes, connectors, icons.
• Trusted by SNU, Stanford, UC Berkeley, CMU, Tsinghua, SJTU, Yonsei, IIT Madras, Monash, Broad Institute.
Example: prompt "encoder–decoder segmentation pipeline with skip connections" → ready architecture diagram in seconds. Reference: paper-banana.org
From submission to camera-ready — and how Hermes shortens each cycle.
• Format to venue template (IEEE/ACM).
• grounded-citations checks every claim links to a real source.
• cite exports clean BibTeX/references.
• Editors assign 2–3 anonymous reviewers.
• critic pre-empts weaknesses before submission.
• factcheck flags unsupported claims.
• Address each point (accept / rebut).
• deepdive gathers new evidence for gaps.
• synthesise merges reviewer feedback.
Loop repeats per round (R1 → R2 → …) until accept; then camera-ready + research-paper-writing polish. Average: 2–4 months per round.
One orchestrator fans out to many specialized workers, then merges results.
• Orchestrator splits the task into independent sub-goals.
• Swarm = N parallel subagents, each with its own context & tools.
• Merge: results aggregated, deduplicated, cross-checked.
• Hermes: delegate_task spawns concurrent workers (no shared context bloat).
1. kimi.com receives the research question (e.g. "compare 2025 VLM agents").
2. → swarm: fans out to subagents — ArXiv sweep, benchmark mining, repo cloning.
3. → …: each worker returns findings; orchestrator synthesizes one report + BibTeX.
• Same pattern in Hermes: 3 delegate_task calls → one literature matrix.
Why: 10× speedup vs serial search, isolated failures, no single context overflow. Pair with synthesise + critic.
Elsevier's research-grade AI workspace (Scopus data) — and the author record it surfaces.
• AI workspace powered by Scopus + Elsevier full-text.
• Deep Research reports: patterns, contradictions, evidence gaps.
• Trust Cards + Claim Radar: sources & contradictions shown.
• Writing Coach, Funding Scout, Author Search, collaborators.
• h-index 6 · 12 publications · 73 citations
• Affiliation: Center for AI Technology, Bangi, Malaysia.
• Active years: 2010–2022.
• Topics: camera calibration, robot localization, image segmentation, OCR, license-plate recognition.
• Profile generated by LeapSpace, Sun Sep 06 2026.
Hermes mapping: deepdive/literature-review ≈ Deep Research · grounded-citations/factcheck ≈ Trust Cards/Claim Radar · cite ≈ Author Search/BibTeX.
Dedicated finders query Crossref / Semantic Scholar — no hallucinated refs like chatbots.
| Tool | Best for | Standout | Styles |
|---|---|---|---|
| Sourcely | Bulk / paragraph | Scans essays, highlights text needing support, summaries | 700+ (BibTeX, RIS) |
| Citely AI | Claim verification | Paste claim → matched to verified DOIs | APA, MLA |
| Grammarly | In-line writing | Flags missing sources in editor, inserts citations | APA, MLA, Chicago |
| Paperpal | MS Word flow | 250M+ articles, search by title/DOI | 10,000+ |
| SciSpace | Partial metadata | Broken URL/author → complete citation | BibTeX, RIS, CSV |
| Writeless | PDF uploads | Filter by min year, inline insertion | APA, MLA, Harvard… |
Beyond find: Scite labels citations support/challenge/mention · Google Scholar (free, manual) · Consensus (Consensus Meter) · manage with Zotero / Mendeley / MyBib. Hermes: cite formats, factcheck verifies, grounded-citations grounds.
Turn your notes into a queryable, agent-editable knowledge base.
• Vault = plain markdown; Hermes reads/writes via the obsidian skill.
• Path from OBSIDIAN_VAULT_PATH or ~/Documents/Obsidian Vault.
• Use [[wikilinks]] + YAML frontmatter (tags, aliases) for structure.
• Two-way sync: edit in Obsidian, Hermes sees it next turn.
• obsidian — search, read, create, edit notes & wikilinks.
• llm-wiki — build interlinked markdown KB.
• synthesise — merge notes into one.
• cite — attach BibTeX to literature notes.
• factcheck / grounded-citations — verify before saving.
Flow: capture → Hermes tags & links → query with search_files → surface in deepdive / literature-review. Your second brain, always current.
Google's experimental AI app platform — verified facts only; function not yet documented publicly.
• Official Google product labelled "Opal [Experiment]".
• Web app (opal.google) loading in a sandboxed iframe.
• Requires Google sign-in (OAuth) to use.
• Requests camera & microphone permissions.
• Exact purpose / feature set is not in the page source.
• Positioned in Google's "experiments" track (like Labs).
• Likely an AI app-/agent-building surface — unconfirmed.
• Check opal.google after sign-in for live capability.
Hermes angle: if Opal is an app/agent builder, it parallels skill_manage (custom skills) & delegate_task (subagents) — but treat as speculation until docs ship.
All installed via hermes skills install, security-scanned, and verified (valid SKILL.md, enabled).
agent-reach · youtube-full · defuddle · resemble-detect
using-agent-skills · setup-matt-pocock-skills · make-interfaces-feel-better · humanizer
browser-harness · i-have-adhd · loopy · loop-library · skillclaw
Everyday commands — Desktop, CLI chat, messaging, shell. (Verified vs current Hermes source, Sep 2026.)
/new · /resume · /sessions · /title · /branch · /compress · /context · /status
/queue · /steer · /bg · /btw · /agents · /stop
/goal · /subgoal · /heartbeat · /loop · /plan · /review · /refine
/model · /moa · /personality · /reasoning · /fast · /approvals · /yolo · /busy · /voice
/skills · /learn · /memory · /init · /tools · /browser
/cron · /suggestions · /blueprint · /kanban
/retry · /undo · /save · /diff · /rollback · /usage · /debug · /help
/sethome · /topic · /commands · /approve · /deny · /pause · /platform · /restart
hermes / hermes chat · -z "prompt" · model · status · doctor · gateway status · --safe-mode · update
Research Publications & Notes • GitHub Repositories