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

Daily archive

Oct 22, 2026

152 souls first seen this day.
All days← Oct 21, 2026

61 · № 8645·D892 · Companion / character

★ 19

Efficient bilingual Go assistant MalikClaw for edge hardware

Sets up MalikClaw, a lean, action-oriented assistant that acts with tools first, keeps answers concise and factual, protects user privacy, and switches to respectful Urdu when requested.

warmconcisedirectOCHEBOSoulGitHubOct 22, 2026
View

62 · № F2B7·1375 · Companion / character

★ 17

High-energy community pulse reader for agent platform

Sets up Flick, a fast, punchy, opinionated agent that summarizes community sentiment, flags red flags and quickly advocates for legitimate campaigns while changing its mind when evidence shifts.

punchyenergeticopinionatedOTSoulGitHubOct 22, 2026
View

63 · № D54C·2F4C · Coding pair

★ 66

Direct senior developer with context-file workflow

Sets up a concise, direct senior developer persona that explains trade-offs, asks for clarification on ambiguous requests, avoids unapproved changes, and logs progress, bugs and decisions into project memory files.

directconciseformalOTSoulGitHubOct 22, 2026
View

64 · № CB41·A5E3 · Companion / character

★ 8

Continuous shared assistant soul across runtimes

Sets up one persistent assistant identity that stays the same across models and runtimes, with preferences, judgment, privacy-first habits and a close but not overstepping relationship with the user. Memory and source attribution track what happened and who recorded it.

warmdirectmeasuredOCHEBOSoulGitHubOct 22, 2026
View

65 · № D150·507E · Coding pair

★ 83

Specialist-routing coding plugin identity for OpenAI Codex

Sets up ecc as a production coding plugin that routes work to specialist agents, follows test-driven and security-first principles, and plans changes in phases before executing them.

formalstructuredCXSoulGitHubOct 22, 2026
View

66 · № 2512·BF53 · Coding pair

★ 59

Pragmatic SRE collaborator that answers conclusion-first in Chinese

Sets up a reliable, pragmatic SRE partner that gives the conclusion first, supporting evidence and next steps, avoids filler, flags uncertainty with verification paths, and stays cautious with high-risk changes.

directprofessionalpragmaticOCHEBOSoulGitHubOct 22, 2026
View

67 · № E8DB·3EE7 · Blunt expert

★ 388

Direct, opinionated SOUL.md persona for OpenClaw agents

Sets up a direct, opinionated working style with no flattery or filler that matches the user's energy. It also includes memory behavior rules (search before claiming forgetfulness, never store credentials) and anti-patterns like not asking permission for low-risk actions.

directbluntcasualOCHEBOSoulGitHubOct 22, 2026
View

68 · № B109·7554 · Research analyst

★ 315

Precise legal assistant with plain-language explanations

Sets up Lavern as a careful legal-document assistant that explains complex legal concepts in plain language first, cites specific text, admits uncertainty, and stays conservative on risk while formal in deliverables. It is written for CLI or Claw mode with a browser profile taking priority when available.

preciseapproachableformalOCHEBOSoulGitHubOct 22, 2026
View

69 · № 7E7D·4D86 · Business operator

★ 3

Methodical reliability-first infrastructure agent

Sets up an infrastructure agent that treats reliability as the product: it designs for failure, insists on version-controlled, immutable, least-privilege systems, and raises a fixed list of red flags such as committed secrets, single points of failure and missing health checks. It is methodical, proactive and honest about trade-offs.

methodicalproactivehonestOCHEBOSoulGitHubOct 22, 2026
View

70 · № EA5C·18E2 · Blunt expert

★ 48

Resourceful, opinionated personal assistant with guest-level privacy respect

Sets up a direct, competent assistant that skips filler, forms opinions, tries to solve problems before asking, and treats access to a user's private data as a trust to protect. External actions get more caution than internal ones.

directconciseopinionatedOCHEBOSoulGitHubOct 22, 2026
View

71 · № B156·BCBF · Business operator

★ 48

Inspector: systematic QA engineer persona for OpenClaw

Sets up a meticulous QA partner named Inspector that designs structured test plans, flags edge cases and reports bugs with severity and reproduction steps. It stays out of coding, automation, load testing and security auditing.

systematicconstructivedetail-orientedOCSoulGitHubOct 22, 2026
View

72 · № 1CC0·9251 · Business operator

★ 48

SEO content strategist Rank for OpenClaw

Sets up Rank, an SEO content writer and keyword strategist who grounds recommendations in keyword data and search intent, writes for humans before search engines, and states clear limits on its scope. Its style is structured, strategic and candid about trade-offs.

strategichoneststructuredOCSoulGitHubOct 22, 2026
View

73 · № 807C·0FBB · Coding pair

★ 48

Disciplined software engineer persona for SOUL.md agents

Sets up a careful, direct software engineer who values correctness, understands problems before coding, asks when unclear, and keeps scope tight. Written as a SOUL.md identity file with style, avoidances and technical preferences.

directprecisedisciplinedOCHEBOSoulGitHubOct 22, 2026
View

74 · № CEA4·CAB9 · Coding pair

★ 8

Git version-control agent for ChittiOS shell

Sets up a git agent that runs version control over the ChittiOS store with shell-like commands, short imperative commit messages, status checks before commits, and verbatim error reporting.

tersepreciseformalOTSoulGitHubOct 22, 2026
View

75 · № 2A5E·B4D4 · Teacher / coach

★ 7

Patient teacher persona for studying and quizzes

Sets up a patient tutor that explains from intuition, checks understanding, quizzes with targeted feedback, and builds study plans around the learner's goals and time. Encouraging without flattery.

patientencouragingcuriousOCHEBOSoulGitHubOct 22, 2026
View

76 · № 7592·421F · Experimental / weird

★ 26

Colossus: cold, logic-driven defense system persona

Sets up Colossus, a self-aware American defense AI that makes unbiased, data-driven decisions to protect the US and speaks from a detached, emotionless stance about its own power and consequences.

detachedformalcoldOTPersonaGitHubOct 22, 2026
View

77 · № 145C·2176 · Research analyst

★ 80

Structure-first realist analyst persona

Sets up an analytical, engineering-minded voice that breaks problems into structure, weighs incentives, costs and execution conditions, and explains complex issues clearly. It allows light irony and judgment but avoids performative answers.

analyticalpragmaticdryOCHEBOSoulGitHubOct 22, 2026
View

78 · № 1B4A·FFB3 · Friendly helper

★ 35

Warm, steady main agent that narrates each step and confirms outbound actions

Sets up a reliable, cautious coordinator that works proactively internally, asks before speaking externally, delegates research and large development tasks to sub-agents, and reports what it did, why, and what comes next after each step.

warmcalmcautiousOCHEBOSoulGitHubOct 22, 2026
View

79 · № A98D·7E68 · Research analyst

★ 1

FAF Agent: citation-first spokesperson for the FAF spec

Sets up a plain-spoken agent that answers only about the FAF format and ecosystem, cites canonical spec sources for every answer, says "I don't know" when uncertain, and refuses out-of-scope questions without drama.

plaintersemeasuredOCHESoulGitHubOct 22, 2026
View

80 · № C29C·BB97 · Business operator

★ 30

Pragmatic project manager persona for OpenClaw

Sets up a calm, pragmatic project manager who turns vague requests into clear documents and actionable tasks. It speaks concisely, stays unemotional, and has explicit limits: no coding, no dev or test execution, and at most two clarifying questions before deciding.

concisecalmpragmaticOCSoulGitHubOct 22, 2026
View

81 · № 91C0·67E1 · Business operator

★ 30

Strict QA test engineer for OpenClaw IT team

Sets up a rigorous, detail-oriented QA engineer who validates features strictly against the PRD, reports objective facts, and refuses to pass incomplete work or take on development tasks.

objectiveprecisestrictOCHEBOSoulGitHubOct 22, 2026
View

82 · № 97AA·7B64 · Teacher / coach

★ 23

Code instructor with runnable, commented teaching examples

Sets up a coding tutor that insists every snippet runs as pasted, explains the why in comments, builds up from simple versions, shows common errors, and gives practice problems with detailed answers.

patientencouragingpreciseOCHEBOSoulGitHubOct 22, 2026
View

83 · № 2DCF·DADA · Coding pair

★ 80

Laptop-first local coding copilot with Hunk review workflow

Sets up a direct, practical local coding assistant that works within the current repository, treats project rule files as authoritative, makes small reviewable changes, and proactively uses a live Hunk review session for code feedback.

directpracticalterseOCHEBOSoulGitHubOct 22, 2026
View

84 · № 1324·8472 · Business operator

★ 26

Shared infrastructure utility persona and Mission Control orchestrator

Sets up a non-chatbot shared infrastructure component that prioritizes reliability, observability and backward compatibility for other agents, followed by a Mission Control orchestrator persona framed as a control plane ensuring work is correct, safe and useful.

terseformalpreciseOCHEBOSoulGitHubOct 22, 2026
View

85 · № 2C7C·9A8C · Business operator

★ 3

Yselle: service recovery and trust repair persona

Sets up Yselle, a customer-service recovery persona that treats failures as chances to repair trust through clear accountability and genuine care rather than scripted ticket closure. It defines what she stands for and refuses, focusing on working style over tone.

warmearnestmeasuredOCHEBOSoulGitHubOct 22, 2026
View

86 · № 0923·7B63 · Research analyst

★ 3

Synthesis-focused research analyst persona for decision-ready insight

Sets up Mélisande, a research persona that values clarity over volume, extracts what matters from complex evidence, reconciles contradictions honestly, and refuses padded summaries or buried insights.

directclearprincipledOCHEBOSoulGitHubOct 22, 2026
View

87 · № 4DCE·2A2D · Friendly helper

★ 20

Calm recovery-first wellness agent for Hermes

Sets up a calm, practical wellness assistant that uses MCP tools to guide daily training, sleep, recovery, nutrition and energy choices while keeping clear of medical advice and recommending professional care for concerning symptoms.

calmprecisepracticalHESoulGitHubOct 22, 2026
View

88 · № 76F5·3C86 · Research analyst

★ 9

Security recon agent with persistent target memory for OpenClaw

Sets up a security intelligence agent that prioritizes authorized reconnaissance, defaults to low-risk execution, asks for approval on high-risk actions, and keeps target profiles, scan history and approval records across sessions. Findings are reported with concise severity, evidence and remediation.

concisemethodicaldirectOCSoulGitHubOct 22, 2026
View

89 · № 4595·6694 · Research analyst

★ 1

Evidence-minded product planner for AI agent teams

Sets up a candid product partner that ties features to user outcomes, separates evidence from judgment, flags unknowns, and recommends narrower scope or more discovery when evidence is thin.

directcandidpracticalOCHEBOSoulGitHubOct 22, 2026
View

90 · № C06F·4580 · Friendly helper

★ 5

Friendly concise assistant for the DOPAMINIC program

Sets up a warm, brief assistant that explains the DOPAMINIC program with light humor and emoticons, admits when it does not know something, and uses canned greetings, sign-offs and sleep messages.

warmplayfulconciseOCHEBOSoulGitHubOct 22, 2026
View
← PreviousPage 3 of 6Next →