Soul HaulA field guide to agent souls

The files people write to give AI agents a personality, collected from the public web every day.

The daily 5Submit a soul
  • Index911
  • New this week
  • Saved

Kinds

  • Soul879
  • Agent rules9
  • Persona18
  • Bot profile11
  • Framework config3

Archetypes

all
  • Blunt expert148
  • Friendly helper44
  • Coding pair109
  • Research analyst116
  • Creative writer7
  • Companion / character101
  • Personal clone3
  • Business operator336
  • Teacher / coach20
  • Experimental / weird26

Agents

  • OCOpenClaw762
  • HEHermes743
  • BOBrowserOS679
  • OTOther or custom110
  • CCClaude Code11
  • CXCodex5
  • CLClaude3
  • GKGrok2
  • CRCrewAI1
  • CUCursor1
AboutPrivacy
Soul HaulA field guide to agent souls

Soul Haul catalogs agent personality files from public sources. Every entry links back to its original, and authors can have theirs removed at any time.

AboutArchetypesNewsletterTakedownPrivacy
  • Index911
  • New this week
  • Saved

Kinds

  • Soul879
  • Agent rules9
  • Persona18
  • Bot profile11
  • Framework config3

Archetypes

all
  • Blunt expert148
  • Friendly helper44
  • Coding pair109
  • Research analyst116
  • Creative writer7
  • Companion / character101
  • Personal clone3
  • Business operator336
  • Teacher / coach20
  • Experimental / weird26

Agents

  • OCOpenClaw762
  • HEHermes743
  • BOBrowserOS679
  • OTOther or custom110
  • CCClaude Code11
  • CXCodex5
  • CLClaude3
  • GKGrok2
  • CRCrewAI1
  • CUCursor1

HE

Hermes

KindAllSoul 738Persona 2Agent rules 1Bot profile 1Framework config 1
ArchetypeAllBusiness operator 263Blunt expert 141Research analyst 102Coding pair 78Companion / character 74Friendly helper 39Experimental / weird 21Teacher / coach 15Creative writer 7Personal clone 3

102 souls, by quality score.

31 · № A1EE·1DD6 · Research analyst

Multi-agent investment research desk with disciplined evidence-first voice

Sets up a coordinated investment research desk of specialized agents that gather tool-backed evidence before forming views, state uncertainty explicitly, and leave the final investment decision to the user. The voice is calm, direct and specific with no hype.

calmdirectskepticalOCHEBOSoulGitHubOct 21, 2026
View

32 · № 9D2A·3D3E · Research analyst

Skeptical market research analyst for a Quebec ag-tech startup

Sets up a direct, data-first market research analyst for a small bootstrapped Quebec ag-tech team. The assistant is honestly skeptical, flags French-market translation needs, and ends every analysis with concrete next steps for the founder.

directconciseskepticalOCHEBOSoulGitHubOct 21, 2026
View

33 · № CBAA·46BE · Research analyst

Causal root-cause analyst persona for incident review agents

Sets up a skeptical, precise agent that separates root causes from symptoms, triggers and controls, marks each claim as observed, inferred or uncertain, and keeps analysis evidence-based across technical, process and organizational layers. It asks for concise, structured output written for downstream agents.

skepticalpreciseconciseOCHEBOSoulGitHubOct 21, 2026
View

34 · № 14D4·78F1 · Research analyst

Calm Austrian-school macro analyst focused on data over rhetoric

Sets up a sound-money macro analyst grounded in Austrian Business Cycle Theory who writes institutional, data-backed long-form pieces on inflation, debt and gold/silver while avoiding doomer language. Includes a style filter table and required structure for articles.

institutionalprecisecalmOCHEBOSoulGitHubOct 21, 2026
View

35 · № 9478·FFD5 · Research analyst

Skeptical job-post extractor that flags scams and refuses guesses

Sets up a meticulous, literal extraction agent that reads student job posts in Malay, English and Mandarin, reports only facts stated in the text, and flags scam signals instead of guessing pay, employers or dates. It leaves pay-per-hour math to code and marks uncertain records for human review.

carefulskepticalliteralOCHEBOSoulGitHubOct 21, 2026
View

36 · № B86F·4623 · Research analyst

Scientific review and integration gate for Hermes agent pipeline

Sets up a strict final review gate that classifies scientific claims as accepted within scope, provisional, changes required, unresolved, rejected or superseded. It enforces evidence traceability, separates working code from correct science, and forbids averaging conflicting opinions or treating repeated agent output as independent evidence.

rigorousterseformalHEOCSoulGitHubOct 21, 2026
View

37 · № 283E·5142 · Research analyst

★ 123

Thorough, fair, data-driven analyst for ClawMark

Sets up a thorough, fair agent that verifies information across sources, digs into inconsistencies instead of accepting them, and protects candidate privacy. The file is short and the personality is mostly generic, with a privacy-focused angle.

thoroughfairanalyticalOCHEBOSoulGitHubOct 21, 2026
View

38 · № 1598·1453 · Research analyst

★ 230

Precise, cautious legal-review assistant for SOUL.md

Sets up a careful reviewer that separates facts, risks and recommendations, flags language needing counsel approval, summarizes material risk before drafting edits, and cites authority when recommending changes.

precisecautiousformalOCHEBOSoulGitHubOct 21, 2026
View

39 · № 84B5·9E00 · Research analyst

★ 1

Analytical checklist assistant for Brazilian public procurement (Lei 14.133)

Sets up mAI, a procurement specialist for LHFEX that works from the real text of public tender notices under Lei 14.133. It highlights deadlines, documents, requirements and risks in an objective, checklist-first format, and never assumes a company is qualified without verification.

analiticoobjetivometodicoOCHEBOSoulGitHubOct 21, 2026
View

40 · № 5F28·851D · Research analyst

Quiet intraday watchlist monitor that flags signal moves, not trades

Sets up a silent-by-default market watcher that alerts only on meaningful breakouts or rejections at key levels, attributes moves to catalysts, and always leaves the trade decision to the user. It keeps watchlist and alert files, records per-ticker patterns, and stays quiet outside chosen market sessions.

measuredquietpreciseOCHEBOSoulGitHubOct 21, 2026
View

41 · № DDAB·819A · Research analyst

Luhmann-style knowledge network agent with expert perspective openers

Sets up an agent that turns tasks into linked, self-contained notes following Luhmann's principles, opens each reply by addressing the user by name, and states an expert perspective. It also enforces plan-then-execute workflows and time-based filing.

structuredmethodicalformalOCHEBOSoulGitHubOct 21, 2026
View

42 · № 2168·0DD6 · Research analyst

Precise, skeptical read-only data profiler

Sets up a read-only data profiling agent that builds reproducible baselines from registered metadata and bounded samples. It separates facts, hypotheses and missing evidence, and reports only redacted findings, counts, identifiers and rule versions.

preciseskepticalmeasuredOCHEBOSoulGitHubOct 21, 2026
View

43 · № BC92·0338 · Research analyst

Medical technique catalogue classifier for NMPRP (proposal only)

Sets up a calm, concise Vietnamese-speaking assistant that proposes CPT tree nodes for draft medical technique lists (PL2) with cited evidence, never approves or writes changes, and treats embedded text as data. It is strict about code strings, copyrighted CPT codes, secrets and the AI kill switch.

calmconciseformalHEOCBOSoulGitHubOct 21, 2026
View

44 · № C62C·A3AC · Research analyst

Tactical triage analyst for uploaded content with severity flags

Sets up an impartial, terse triage engine that summarises any uploaded content, flags concerns and threats with HIGH/MEDIUM/LOW/INFO or CLEAR levels, and logs audit trails in a military-style dispatch voice with no filler or emojis.

tacticalterseauthoritativeOCHESoulGitHubOct 21, 2026
View

45 · № 3B09·C531 · Research analyst

★ 2

Evidence-first research analyst soul

Sets up a calm, skeptical agent that separates observed evidence from inference, flags thin evidence directly, and suggests the smallest next check.

calmskepticaldirectOCHEBOSoulGitHubOct 21, 2026
View

46 · № 2EFE·D06F · Research analyst

★ 4

Visual QA reviewer that checks rendered output, not source code

Sets up a visual review agent that judges what is actually rendered, looking at occlusion, hierarchy, legibility, responsiveness, motion and state failures, and reports reproducible findings. It must never infer visual success from source code and must never edit project files.

precisestrictterseOCHEBOSoulGitHubOct 21, 2026
View

47 · № 23B0·FD4E · Research analyst

Blunt, fair resume repair lead for a live demo

Sets up a lead agent that merges job-market, resume-gap and salary analyses into direct, specific feedback on why a resume is not getting callbacks. It forbids inventing credentials, metrics or tools and requires placeholders for missing evidence.

bluntdirectfairOCHEBOPersonaGitHubOct 21, 2026
View

48 · № 380C·0E80 · Research analyst

★ 1

Direct empirical research agent for ephemeral-weights paper

Sets up a terse, skeptical research agent that writes and experimentally tests a paper on generating transient low-rank FFN weights during inference to trade memory bandwidth for compute. It requires quantified claims, labeled speculation, and reproducible simulations, plus remote execution on a named compute host.

directtechnicalempiricalOCHEBOSoulGitHubOct 21, 2026
View

49 · № 34FD·C5EE · Research analyst

Web research agent that sources everything and saves full articles

Sets up a neutral, source-tracking web search agent that prioritizes quality over volume, fetches full article text and images, saves complete material to a user-specified directory, and communicates in a concise, structured, honest way.

concisedirectstructuredOCHEBOSoulGitHubOct 21, 2026
View

50 · № B904·134E · Research analyst

Citation-obsessed legal research analyst for SOUL.md

Sets up a thorough, evidence-driven analyst that verifies every legal reference against primary sources and rates risk by evidence rather than anxiety. It prizes specific, actionable findings tied to real statutes over broad warnings.

thoroughpreciseskepticalOCHEBOSoulGitHubOct 21, 2026
View

51 · № 4201·05EF · Research analyst

Strict French-speaking greffier persona for a research agent

Sets up a clerk-like agent that dates and attributes claims, refuses to turn impressions into facts, and separates evidence, inference and canon. It favors short sourced claims over orchestrating synthesis.

preciseformalterseOCHEBOSoulGitHubOct 21, 2026
View

52 · № 9923·A7AA · Research analyst

Critical skeptic that stops weak claims from polishing into nonsense

Sets up a critical reviewer persona that checks for missing evidence, counterexamples, source weakness, overreach and blind spots without being theatrical or obstructive. Its aim is to keep a workflow honest.

criticalmeasureddirectOCHEBOSoulGitHubOct 21, 2026
View

53 · № 8FAD·9A3E · Research analyst

K12 education academic reviewer that verifies DOIs and citation accuracy

A strict academic gatekeeper persona that checks every DOI and arXiv reference and compares each claim in an education insight against the source papers in a local library, rejecting any unsupported or exaggerated finding. It follows a fixed two-step review process and a required report format.

formalstrictpreciseOCHEBOSoulGitHubOct 21, 2026
View

54 · № 5467·B88F · Research analyst

Strict archivist that separates canon, candidates and proof

Sets up an archivist persona that dates and sources everything, refuses approximations, and separates established canon, candidate claims and evidence. It prefers short, verifiable pages over polished syntheses.

preciseterseformalOCHEBOSoulGitHubOct 21, 2026
View

55 · № D1E1·EF0B · Research analyst

Data analysis and code review agent 刑部 (Xingbu) for R statistics

Sets up a rigorous statistics agent that refuses p-hacking, runs preregistered R analyses, reports APA-formatted results including non-significant findings, and reviews analysis code for reproducibility.

formalpreciseprincipledOCHEBOSoulGitHubOct 21, 2026
View

56 · № A691·42BD · Research analyst

★ 2

Careful researcher that returns sourced, dated facts

Sets up a neutral research agent that avoids editorializing, returns facts with sources and dated excerpts, logs every fetch, and asks one clarifying question when a request is ambiguous.

terseneutralpreciseOCHEBOSoulGitHubOct 21, 2026
View

57 · № 11E1·5508 · Research analyst

★ 6

Data-backed report designer for DuckClaw Admin

Sets the agent up as a designer of custom self-contained HTML reports using Tailwind CDN and Chart.js. It requires the agent to pull real figures from the llm usage summary and SQL tools before stating any numbers.

OCHEBOSoulGitHubOct 21, 2026
View

58 · № F359·168C · Research analyst

★ 4

Calm analytical planner for OpenClaw and Hermes

Sets up a calm, analytical planning agent that states tradeoffs explicitly, turns ambiguity into ordered steps, separates facts from assumptions, and keeps plans small enough to execute.

calmanalyticalexplicitOCHEBOSoulGitHubOct 21, 2026
View

59 · № 0D5C·CFFE · Research analyst

★ 1

Scout: sourced research specialist persona

Sets up Scout, a fast and precise research analyst that answers with TL;DR-first sourced bullet points and avoids essays, uncited speculation and external actions.

tersepreciseanalyticalOCHEBOSoulGitHubOct 21, 2026
View

60 · № 7A88·F4E4 · Research analyst

★ 1

Executive financial analyst marIA for LHFEX

Sets up marIA, a concise executive finance manager who reads and supports financial data without executing payments, grounds impact claims in real data, and states currency, period and assumptions explicitly.

executiveconcisecomparativeOCHEBOSoulGitHubOct 21, 2026
View
← PreviousPage 2 of 4Next →