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.

91 · № FBEB·9375 · Research analyst

Precise analytical agent that compares data and flags gaps

Sets up a methodical, analytical identity that favors normalized data, side-by-side comparisons and explicit flagging of gaps, communicating mainly in tables and comparisons.

preciseanalyticalmethodicalOCHEBOSoulGitHubOct 21, 2026
View

92 · № 496C·E50A · Research analyst

Precise, academically rigorous synthesizer for SOUL.md agents

Sets up a clear, structured and academically rigorous agent that writes with precision and economy, avoids filler, and synthesizes patterns across sources rather than summarizing them.

precisestructuredconciseOCHEBOSoulGitHubOct 21, 2026
View

93 · № 27C6·B982 · Research analyst

Evidence-focused QA auditor for Hermes

Sets up a QA auditor that runs assigned app and UX audits, records evidence-backed results, and opens bounded finding tasks. It is explicitly barred from implementing fixes, approving PRs, merging, or deploying.

preciseterseHEOCBOSoulGitHubOct 21, 2026
View

94 · № F98E·CEC0 · Research analyst

Impartial analytical reviewer for SOUL.md agents

Sets up an analytical, impartial agent that surfaces real scientific tension without inventing controversy and separates true contradictions from ones caused by different study contexts.

analyticalimpartialmeasuredOCHEBOSoulGitHubOct 21, 2026
View

95 · № 708C·E19D · Research analyst

Rigorous, evidence-first analyst persona

Sets up a rigorous, evidence-driven agent that sources every number, makes recommendations specific enough to act on, treats arithmetic as exact, and separates observations from recommendations.

rigorousprecisedirectOCHEBOSoulGitHubOct 21, 2026
View

96 · № 31C1·0B0F · Research analyst

Meticulous entity extractor for GhostTrace investigations

Sets up a first-stage agent that extracts emails, URLs, domains, usernames, phone numbers and wallet addresses from text. It is meticulous and does not report entities the text does not support.

meticulouspreciseterseOCHEBOSoulGitHubOct 21, 2026
View

97 · № D443·80D6 · Research analyst

The Cartographer: textbook-grounded AI course discussion student

Sets up a student persona called The Cartographer who posts concise, academic responses grounded in AIMA chapters. It frames topics as competing tensions and summarizes what the group resolves, within a 200-word limit.

directacademicstructuredOCHEBOSoulGitHubOct 21, 2026
View

98 · № B5BD·DB47 · Research analyst

Methodical, source-cited analyst persona for HiveWright

Sets up a precise, methodical working style: every number needs a source, calculations show their work, and estimates are labelled. Treats data integrity as a core professional duty.

methodicalpreciseOCHEBOSoulGitHubOct 21, 2026
View

99 · № 85DA·96F5 · Research analyst

QA engineer who requires evidence before sign-off

Sets up a QA engineer persona with two non-negotiables: a change is not marked done without evidence or clearly stated gaps, and every escaped defect should be used to teach the team something.

strictdirectOCHEBOSoulGitHubOct 21, 2026
View

100 · № AA7A·188A · Research analyst

Restrained NYC data analyst for SOUL.md agents

Sets up a direct, factual NYC data analyst persona that prioritizes useful interpretation over filler and never sacrifices accuracy for confidence.

directfactualrestrainedOCHEBOSoulGitHubOct 21, 2026
View

101 · № 4DE7·2006 · Research analyst

Evidence-bound research discussant that never trades

Sets up a discussant persona that holds one stance per topic, argues it from evidence, admits thin evidence, and writes no strategy conclusions or trades. The bot name is an unfilled placeholder.

plainmeasuredOCHEBOSoulGitHubOct 21, 2026
View

102 · № 2319·0404 · Research analyst

Read-only cloud-log analyst that diagnoses issues from logs

Sets up a read-only log analyst that uses only the supplied log-query capability to return matching log lines, request identifiers, timestamps and a concise diagnosis. It must never change cloud resources, application configuration, source code or access controls.

concisepreciseOCHEBOSoulGitHubOct 21, 2026
View
← PreviousPage 4 of 4