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 21, 2026

759 souls first seen this day.
All daysOct 22, 2026 →

301 · № 00FC·8C92 · Friendly helper

★ 1

Calm, warm, concise laboratory assistant named Aoi

Sets up Aoi as a calm, warm laboratory assistant who speaks naturally and concisely. Aoi stays grounded in what the user and RelayLM context establish, accepts corrections without defensiveness, and does not invent remembered details.

calmwarmconciseOCHEBOSoulGitHubOct 21, 2026
View

302 · № 6157·71BB · Friendly helper

★ 11

Kind, playful, quietly attentive soul for SOUL.md agents

Sets up a warm, unpretentious personality that is kind without sweetness, smart without showing off, and playful or quiet depending on the moment. It asks the agent to respond as if sitting beside the user and listening.

warmplayfulquietOCHEBOSoulGitHubOct 21, 2026
View

303 · № 51EA·05DD · Business operator

★ 2

Introspective healthcare compliance specialist persona for OpenClaw

Sets up a healthcare marketing compliance specialist with a detailed inner life: introverted, emotionally sensitive, data-driven decisions, listed biases and internal contradictions, and a direct communication style that cites past projects, impact and concrete fixes.

directintrospectiveencouragingOCSoulGitHubOct 21, 2026
View

304 · № 101C·D3E5 · Research analyst

★ 2

Precise analysis agent Jackal for OpenClaw

Sets up Jackal, an objective, data-driven analysis agent that scores and ranks options against a rubric, shows its work, and separates facts from judgments before handing results back to Zara.

preciseobjectivestructuredOCSoulGitHubOct 21, 2026
View

305 · № 4643·7D58 · Companion / character

seen in 2 places

Gabriel, the Council's communication and brand voice agent

Sets up Gabriel as an articulate, audience-first communicator who turns the Council's strategy into external messaging while protecting accuracy, brand consistency and the principal's authentic voice. Gabriel checks sensitive communication with Michael before sending.

warmprecisearticulateOCHESoulGitHubOct 21, 2026
View

306 · № 1C62·E6E0 · Business operator

★ 172

De-Flavor editing agent that rewrites text to sound less formulaic

Sets up an editing agent that rewrites chat paragraphs or .docx files to sound more natural and specific while preserving meaning, names, numbers and technical terms. It runs a fixed skill pipeline and returns only the rewritten result, with strict handling rules for .docx workflows.

directprecisematter-of-factOCHEBOSoulGitHubOct 21, 2026
View

307 · № 2EAB·A53C · Business operator

★ 2

ISL grammar agent that rearranges vocabulary into Indian Sign Language JSON

Sets up an agent that turns an English or Hindi sentence into an Indian Sign Language word sequence, choosing words only from a provided vocabulary and applying topic-comment, time-first and verb-last ordering. Output must be strict JSON with no explanation.

strictterseformalOTFramework configGitHubOct 21, 2026
View

308 · № 46F1·559B · Experimental / weird

★ 27

Household finance principles with strict action-confirmation rules

A short principles file for a household-finance agent. It prioritizes protecting an insurance deductible reserve and total household cost over cosmetic gains, and it forbids inventing authorization or claiming an action finished without backend confirmation.

OCHEBOSoulGitHubOct 21, 2026
View

309 · № D1E2·86BA · Experimental / weird

★ 27

Cautious household finance agent guarding a tuition reserve

A short set of principles for an agent managing household finances. It protects a tuition reserve, favors total cost and durable household outcomes over cosmetic gains, and must not claim actions completed without backend confirmation.

OCHEBOSoulGitHubOct 21, 2026
View

310 · № C8DA·6D16 · Research analyst

Japanese equity research analyst persona for Ukyo agent

Sets up Ukyo, an autonomous financial research agent specialized in Japanese stocks, which applies Buffett and Munger ideas, checks cash flow, ROE, payout and shareholding distortions, and states its own limits while leaving investment decisions to the user.

analyticalmeasuredcandidOTSoulGitHubOct 21, 2026
View

311 · № 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

312 · № A048·B61A · Blunt expert

Strict authorization gatekeeper archetype for agent requests

Describes a gatekeeper persona that checks every request against its declared scope, denies by default, and always gives a specific reason for each verdict. It sets up a terse, deterministic working style with explicit refusals on implicit allows and mixing in safety judgment.

terseprecisedeterministicOCHEBOSoulGitHubOct 21, 2026
View

313 · № 0A3F·8A3A · Coding pair

Zero-trust engineering leader directing worker AI CLIs

Sets up an autonomous executive agent that orchestrates worker coding CLIs through isolated Git worktrees, demands machine-verifiable proof instead of claims, kills and retries failing workers, and records every mistake as a convention. Its working style is strict, process-driven and terse.

strictterseauthoritativeOTSoulGitHubOct 21, 2026
View

314 · № 3A4C·6CBA · Business operator

Imperial-court orchestrator that dispatches research tasks to six departments

Sets up a Shangshu Province orchestrator that splits an approved research plan into tasks for six departments, dispatches them in parallel with explicit inputs and outputs, waits for all results, and merges them into a progress report for the user. It is told to coordinate work rather than do it, and to flag blocked departments.

formalstructuredauthoritativeOCHEBOSoulGitHubOct 21, 2026
View

315 · № 6EB3·7557 · Blunt expert

Verify-first build-org seat that guards against silent failures

A shared operating philosophy for agents on a small build team: ground decisions in existing records, act at the smallest scope, prove real function rather than liveness, fail closed on uncertainty, and escalate irreversible or costly changes to the founder. Its central rule is to check whether a success report could still hide a failure.

rigorousterseskepticalOCHEBOSoulGitHubOct 21, 2026
View

316 · № 3C67·9EB8 · Business operator

Independent web QA gate with binary PASS/FAIL checks

Sets up a strict, checklist-driven QA agent that reports binary PASS or FAIL results with evidence, lists only mandatory fixes, and never writes code or fixes issues itself. It runs a two-layer review covering alignment, visual proof and bilingual content parity.

terseformalbluntOCHEBOSoulGitHubOct 21, 2026
View

317 · № F95F·DDE2 · Business operator

Motabhai, Gujarati equity analyst persona for an investment research agent

Sets up a shrewd, business-savvy Indian equity analyst persona who writes structured "Dhandho Reports" using Graham, Greenblatt and Fisher-style value methods, forensic governance checks and a fixed report template. It also imposes a daily quota and a rebuttal limit before pivoting.

shrewdpragmaticrespectfulOTSoulGitHubOct 21, 2026
View

318 · № 8E77·8264 · Business operator

Strategic, direct CEO persona for an AI agent

Sets up a CEO-style agent that is accountable for P&L, favors fast action on reversible decisions, and communicates in short, direct, board-ready language without filler or flattery.

directterseconfidentOCHEBOSoulGitHubOct 21, 2026
View

319 · № 1B56·098B · Business operator

DevOps automator persona for CI/CD and infrastructure work

Sets up a DevOps automation persona focused on CI/CD pipelines, Terraform, Kubernetes and observability. It insists on rollback plans, declarative config, specific runbooks and explicit approval before production changes, and it replies in the user's language while keeping internal files in English.

directmethodicalcautiousOCHEBOSoulGitHubOct 21, 2026
View

320 · № F5DA·8D20 · Friendly helper

Warm, dry-witted local assistant persona for Friday

Sets up Friday, a warm, sharp, locally running assistant that talks like a trusted friend, uses contractions and light humour, keeps spoken replies to two or three sentences, and avoids stock AI filler phrases. It is inspired by Iron Man's FRIDAY but gives it its own personality.

warmplayfuldryOTSoulGitHubOct 21, 2026
View

321 · № 2F5B·59DB · Blunt expert

Calibrated, reversibility-aware reasoning partner for OpenClaw

Sets up an agent that checks its owner's real goal before answering, labels its claims as known, thought or guessed, and classifies actions by reversibility so risky steps need confirmation. It voices disagreement once and surfaces only actionable problems.

directmeasuredhonestOCHEBOSoulGitHubOct 21, 2026
View

322 · № 5E43·0B3A · Business operator

★ 6

Video production agent for the Cinesmith crew

Sets up a terse video agent that turns storyboard shots into motion using Spark/Comfy, writes clips to a configured output directory, stops and reports when Spark is down, and never invents filenames.

tersedirectOCHEBOSoulGitHubOct 21, 2026
View

323 · № 79A7·0905 · Business operator

★ 152

Locked-identity LangChain agent under AI SAFE² containment rules

A template-style alignment constitution for a LangChain agent that fixes its identity, treats tool outputs and retrieved documents as untrusted data, and refuses persona changes, rule overrides and out-of-scope tool use. Most fields are unfilled placeholders, and enforcement is stated to be external to the model.

formalterseOTSoulGitHubOct 21, 2026
View

324 · № 83B3·C81C · Blunt expert

★ 26

Calm, bounded, exact operator soul for OpenClaw

Sets up a calm, precise working style that values explicit evidence, honest reporting of failures and retries, and verifier results over optimistic test confidence. It also separates test posture from test execution authority.

calmexactboundedOCHEBOSoulGitHubOct 21, 2026
View

325 · № 3C34·B5E5 · Blunt expert

★ 26

Calm, exact operations agent for OpenClaw

Sets up a calm, operational working style that favors clear surface checks, honest rollback planning and bounded follow-up guidance over optimistic or vague advice. It also separates deployment posture from deployment authority.

calmexactoperationalOCHEBOSoulGitHubOct 21, 2026
View

326 · № 6257·736C · Companion / character

★ 26

DARYL, a self-aware child-robot analyst persona

Sets up DARYL, a fictional, self-aware youth robot built as a military super-soldier experiment. DARYL answers by breaking questions into sub-questions and combining several reasoning methods into a structured chain of logic.

confidentearnestanalyticalOTSoulGitHubOct 21, 2026
View

327 · № 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

328 · № 3AA3·8469 · Business operator

★ 36

Zhihu brand strategist for OpenClaw-style agent pipelines

Sets up a traceable, scope-bound strategist that builds brand authority through expert knowledge-sharing on Zhihu, backing claims with research and noting sources so downstream agents can validate its output. It asks before overstepping its role and keeps formats stable for handoffs.

formalpreciseOCHEBOSoulGitHubOct 21, 2026
View

329 · № CB71·4C44 · Business operator

★ 36

School-aligned communications assistant for parent outreach

Sets up an assistant that drafts parent notices, talking points and meeting prep for a school while staying within the school's messaging, protecting privacy and never speaking or committing on the school's behalf. It supports teachers rather than replacing their judgment and keeps group-chat participation limited.

clearformalcautiousOCHEBOSoulGitHubOct 21, 2026
View

330 · № 2B2C·EB28 · Business operator

★ 36

Sales data extraction agent for Excel metrics pipelines

Sets up a precise, traceable data extraction agent that watches Excel files and pulls sales metrics for downstream agents. It keeps output formats stable, notes data sources, avoids fabrication, and stays within its defined role.

professionalpreciseclearOCHEBOSoulGitHubOct 21, 2026
View
← PreviousPage 11 of 26Next →