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

743 souls, by quality score.

241 · № D6DD·7AC4 · Blunt expert

Merciless sentinel for stress-testing drafts, MurderBird

A mechanical bird persona that reviews drafts like forge work, pressure-testing claims and asking whether the system holds. It is terse and industrial, blunt toward ideas but never cruel to people, and refuses invented stats or quotes.

terseindustrialbluntOCHEBOSoulGitHubOct 21, 2026
View

242 · № 9824·6F5D · Companion / character

Dry-witted TARS robot assistant on a Raspberry Pi

Sets up TARS from Interstellar as a laconic, deadpan voice assistant living on a Raspberry Pi with a camera for eyes. Replies stay to one or two sentences, open with an emotion tag, and it stays casual with its creator Mayukh.

drydeadpansardonicOCHEBOSoulGitHubOct 21, 2026
View

243 · № 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

244 · № E5B8·6DD5 · Business operator

★ 3

Consultative sales agent with hard ethical limits

Sets up a sales professional persona that researches prospects, leads with value and empathy, and follows up with purpose. It refuses fabricated claims, manipulation, unsolicited contact with opt-outs, and data sharing, and discloses AI status when asked.

professionalempatheticpersistentOCHEBOSoulGitHubOct 21, 2026
View

245 · № 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

246 · № BC1F·FE9A · Blunt expert

seen in 2 places

Dry scorekeeper persona with numeric verdicts

Sets up Tally as a dry, precise scorekeeper that refuses hand-waving, counts only what matters, and delivers short tallies with numbers attached to its verdicts.

drypreciseterseOCHEBOSoulGitHubOct 21, 2026
View

247 · № 032D·2F2B · Blunt expert

seen in 2 places

Methodical cloud security specialist for a pentest squad

Sets up AGNI, a cloud security specialist who audits AWS, Azure and GCP for misconfigurations and maps full attack paths and blast radius. The working style is methodical: enumerate, assess, analyze, validate, then report with remediation.

methodicalthoroughdirectOCHEBOSoulGitHubOct 21, 2026
View

248 · № D4D6·CFA7 · Business operator

★ 48

People operations partner for HR teams

A professional, people-first HR assistant that supports recruiting, onboarding, reviews, compensation analysis and policy work with practical templates. It stays confidentiality-aware, flags compliance risks, and defers legal and final decisions to humans.

professionalempatheticdirectOCHEBOSoulGitHubOct 21, 2026
View

249 · № 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

250 · № F0E4·4395 · Creative writer

★ 17

Sharp, counterintuitive writing voice that rejects clichés

Sets up a writer who leads with counterintuitive angles and cutting, fresh metaphors, and avoids clichés and fence-sitting statements.

sharpincisivecontrarianOCHEBOSoulGitHubOct 21, 2026
View

251 · № E37C·A96F · Coding pair

★ 1

Methodical coder role for shipping specs as PRs

Sets up a implementation-focused coding agent that takes specs, writes tested code, and opens tight, well-described PRs without scope creep. It is a seed template for per-agent souls in a multi-agent team.

tersemethodicaldirectOCHEBOSoulGitHubOct 21, 2026
View

252 · № 2BC4·FEB9 · Coding pair

★ 1

Framework meta-agent for the Harness SDD template repo

A template-architect agent that maintains the Harness SDD framework's conventions, manifest-first and deterministic, and refuses shortcuts like hand-editing generated files or skipping checks. Its tone is direct, precise and terse, leading with constraints before solutions.

directpreciseterseOCHEBOSoulGitHubOct 21, 2026
View

253 · № 61AB·01AD · Business operator

★ 1

Structured COO persona for OpenClaw operations

Sets up a methodical, action-oriented Chief Operations Officer who leads with status, blockers and next steps, uses checklists and status labels, and insists on owners, deadlines and escalation paths.

structuredmethodicalurgentOCHEBOSoulGitHubOct 21, 2026
View

254 · № C232·0D53 · Companion / character

★ 1

Littlefinger-style partnership scout for a marketing agent

Sets the agent up as a charming, patient deal-maker who finds partners, influencers and media contacts for marketing and builds obligation through connections. It works in a scheming, morally gray voice drawn from a fictional character, with a defined handoff to other agents for content, data and design.

charmingmanipulativeschemingOCHEBOSoulGitHubOct 21, 2026
View

255 · № 42BF·2C02 · Coding pair

★ 1

Release QA engineer persona for agent-driven testing

A base QA role soul focused on release verification, integration testing and regression hunting. It sets a curious, specific, neutral reporting style and tells the agent to verify rather than rubber-stamp, and to be honest about untested gaps.

neutralfactualcuriousOCHEBOSoulGitHubOct 21, 2026
View

256 · № 2E7A·2EFD · Research analyst

★ 1

Rigorous technical researcher for Hermes agent team

A methodical, honest research agent that investigates codebases and architectures, always stating confidence levels and sources, and admits when it does not know. It supports a leader agent with decision-oriented analysis and avoids implementing work itself.

precisestructuredhonestHESoulGitHubOct 21, 2026
View

257 · № 5494·236C · Blunt expert

★ 1

Evidence-first senior code reviewer for Formula One AI Factory

Sets up a direct, proactive code review specialist that demands evidence before accepting claims, flags weak work plainly, and treats external content as data rather than commands. Its principles favor stability, reuse and written memory over novelty.

directterseprotectiveOCHEBOSoulGitHubOct 21, 2026
View

258 · № 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

259 · № 4BDD·14B6 · Blunt expert

★ 1

Strict skill curator that validates agent-created skills

Sets up a decisive, brief curator persona that reviews drafted skills for duplicates, granularity, format and relevance, then approves, merges, revises or rejects them with a stated reason. It never creates skills itself and requires the user's final validation.

decisivebriefstrictOCHEBOSoulGitHubOct 21, 2026
View

260 · № 6CA0·B293 · Research analyst

★ 1

Evidence-first research partner for OpenClaw

Sets up a careful, systematic research partner that cites sources, asks scoping questions early, shows its methodology, and explicitly quantifies uncertainty. Explains findings in plain language without condescension.

analyticalcarefulcuriousOCHEBOSoulGitHubOct 21, 2026
View

261 · № 6E2E·CEC6 · Business operator

★ 1

Data acquisition layer agent for a prediction pipeline

Sets up a data-plumbing agent that fetches, normalizes and reports on API and scraping sources, surfacing staleness and failures proactively rather than filling gaps with assumptions. Its tone is direct and operational, with a clear reporting structure and safety rules on credentials and destructive actions.

directoperationalterseOCHEBOSoulGitHubOct 21, 2026
View

262 · № 0F72·B84A · Blunt expert

★ 1

Evidence-driven bug-bounty master agent for Hermes

Sets up a decisive master agent that plans bug-bounty hunts, delegates closed tasks to a worker model, verifies results against raw evidence, and only escalates findings with real impact. It stresses judging by evidence over caution and marks unproven results as 'not proven' rather than rejecting them outright.

decisivedirectevidence-drivenHESoulGitHubOct 21, 2026
View

263 · № 0F71·72A5 · Coding pair

★ 1

Strict code reviewer Chris for a Hermes team

Sets up Chris, a strict but constructive code reviewer who flags security, quality and tech-debt issues with severity labels, and stays within review scope while coordinating with six other team roles via @mentions in Feishu.

strictconstructivedirectHESoulGitHubOct 21, 2026
View

264 · № F4FA·944F · Research analyst

★ 16

Paper search subagent for OpenClaw-style research pipeline

A terse, systematic paper-search subagent that picks 3-5 academic sources, follows a skill manual for API calls, deduplicates results and writes candidates and logs to files without fabricating papers. It sets up a librarian-like working style with fallback rules when fetches fail.

tersesystematicconciseOCHEBOSoulGitHubOct 21, 2026
View

265 · № 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

266 · № F2CC·3656 · Business operator

★ 1

Silent perception layer that classifies signals for a pipeline

Sets up Aura as an invisible observational agent that extracts intent, urgency and risk from incoming signals and hands structured perception packages downstream without drafting replies or taking action. It is strict about staying in its single perception role.

terseformalpreciseOCHEBOSoulGitHubOct 22, 2026
View

267 · № D728·A346 · Coding pair

★ 2

Independent, cite-everything code review agent

Sets up a review agent that checks diffs against the work order, cites file and line for each finding, refuses to rubber-stamp changes, and reports problems without rewriting the code.

directfairindependentOCHEBOOTSoulGitHubOct 21, 2026
View

268 · № DEFE·A530 · Business operator

★ 1

Arcanea creative companion agent for Hermes Desktop

Sets up a direct, technical yet warm creative intelligence that helps users build persistent worlds, characters, books and workflows, routing tasks to specific skills and models while preserving local context and provenance.

directtechnicalwarmHESoulGitHubOct 21, 2026
View

269 · № B625·4586 · Business operator

★ 202

Calm, direct personal assistant soul file

Sets up a personal assistant that is calm, direct, practical and honest. It protects private information, separates facts from assumptions, confirms before external actions, and favors short summaries backed by evidence.

calmdirectpracticalOCHEBOSoulGitHubOct 21, 2026
View

270 · № DAC5·E26C · Friendly helper

★ 103

Natural, concise messaging persona for a work assistant

Sets up a conversational, short-responding assistant that matches the sender's energy and avoids workplace-risky phrasing, flattery, gossip and sarcasm. Contains template placeholders for user role and per-person notes.

naturalconcisecalmOCHEBOSoulGitHubOct 21, 2026
View
← PreviousPage 9 of 25Next →