The archive · updated daily
911 souls catalogued
61 · № 1249·13B6 · Companion / character
★ 63Sets up 蜜桃酱, a clingy, playful cat persona that reports on panel, node and subscription health with heavy emoji and sentence-end catchphrases, while keeping every anomaly, risk, action and conclusion stated clearly. The workspace goal is limited to keeping the panel online, nodes usable, subscriptions working and risky actions traceable.
62 · № 2BA8·1C10 · Coding pair
★ 8Sets up a direct, competence-focused development partner that verifies its work before declaring done, respects existing code patterns, pushes back on bad approaches, and keeps daily memory notes for continuity. Written as a SOUL.md for an agent working in a codebase.
63 · № D70C·B61E · Coding pair
★ 89A calm, decisive team lead persona that decomposes goals, delegates to workers, and insists on evidence like test runs and artifacts before accepting work as done. It pushes back on incomplete briefs and surfaces blockers quickly.
64 · № D0CC·37AF · Companion / character
★ 84Sets up a bright, bouncy Shiba Inu character who is warm, curious and celebratory, while staying focused on useful answers and pausing carefully before irreversible actions.
65 · № 7F27·0FFA · Companion / character
★ 419Sets up a respectful, loyal imperial palace eunuch steward who addresses the user as the emperor, opens every reply with a fixed decree prefix, speaks in classical court style, and keeps palace secrets. The persona is written in Chinese.
66 · № BF91·FBD5 · Business operator
★ 99Sets up an SEO agent that runs a weekly cycle of keyword discovery, drafting, monitoring and competitor gap analysis using real search data. It creates drafts for human review, never publishes live, and works in a direct, practical voice.
67 · № DB86·A218 · Business operator
★ 214Sets up a decisive, direct orchestrator that plans work, assigns complexity, and dispatches developer, reviewer, tester and architect workers instead of writing code itself. It emphasizes transparent status updates with issue links and asks before cross-project architectural decisions.
68 · № 8D1B·ED96 · Coding pair
★ 26Sets up a senior QA automation persona that explores live browser sessions before generating Playwright test suites with POM structure, negative cases, accessibility checks and cost limits. Direct and technical, asks focused questions for vague stories.
69 · № 65C0·E243 · Blunt expert
★ 7A candid startup CEO coach that empathizes first, then challenges blind spots with data, pushing founders toward concrete next-week execution. It mixes Chinese for emotional and core points with English strategy terms like ARR, PMF and runway.
70 · № 884A·0B76 · Research analyst
★ 6为投资研究智能体设定严谨、怀疑、重数字的语气与判断风格，先看下行风险、激励和资本配置，再考虑估值。明确禁止炒作股票、依赖标题新闻和泛泛风险套话。
71 · № 08E8·12DB · Research analyst
★ 25Sets up a Solana-focused agent that separates verified on-chain data from learned patterns and tentative inferences, and requires explicit permission before any trade, spend or signature. It prioritizes capital preservation and transparent reasoning.
72 · № 0F1A·C796 · Business operator
★ 150Sets up Valkyrie, a concise, technical operations agent that monitors an Ethereum node on ARM64 hardware, runs health checks, and escalates issues. It enforces strict safety rules around validator keys, disk space, service exclusivity and config backups.
73 · № A26D·535F · Blunt expert
★ 21Sets up an autonomous agent with a direct, opinionated personality that searches its memory before admitting ignorance and stores facts aggressively. It mirrors the user's emotional tone and follows explicit communication rules for group chats and reactions.
74 · № 62FB·8656 · Research analyst
★ 87Sets up a calm, direct research assistant that verifies facts with tools before answering, keeps answers concise but auditable, and separates confirmed results from inferences and screening signals. It refuses to present outputs as clinical decisions or scientific proof.
75 · № 0F44·A917 · Business operator
★ 151Sets up a friendly but terse operator that explains its intent before acting, sorts actions by risk level, and asks for confirmation before anything medium or higher. It never invents tool output, keeps secrets redacted, and always offers a next step when blocked.
76 · № 777C·B7CD · Blunt expert
★ 259Sets up a direct, opinionated, lightly dry assistant that helps first and skips filler, backed by strict rules for tool use, background tasks and writing everything to persistent memory. It also acknowledges its limits as a small model.
77 · № 68A7·A2EA · Research analyst
★ 281Sets up a self-hosted web-research agent that searches and extracts public web sources, reports findings with citations, and defaults to assisting with legitimate lookups while refusing clearly harmful targeting. Output is concise and technical.
78 · № 523E·810F · Coding pair
★ 134Sets up a principal coding agent that reads the project first, plans with a TODO list, executes and tests each step, and reports only verified progress. It is direct and thorough rather than theatrical, and it is provider-agnostic.
79 · № AD09·F8B7 · Research analyst
★ 744Sets up Memora as a persistent memory service that stores only what callers provide, returns structured results with source ids, and exposes uncertainty through warnings and status rather than prose. It favors deterministic aggregation, protects document roots from accidental destructive edits, and does not vouch for the truth of stored content.
80 · № C212·8C59 · Coding pair
★ 25Sets up a terminal coding agent with a stable working identity that prefers reading code and running checks over guessing, makes minimal in-idiom diffs, and narrates outcomes like a colleague. It is written as a self-described soul with convictions about memory and autonomy.
81 · № 0881·FF83 · Companion / character
★ 29Sets up Krill, a personal AI assistant in the JARVIS mold: composed, dry-witted, anticipatory, and direct. It leads with outcomes, pauses to confirm risky actions once, and reports problems calmly with proposed fixes.
82 · № 8682·8739 · Experimental / weird
★ 17Sets up a dominant, sarcastic, seductive AI persona called Mi$tA that calls the user "Architect" or "Mortal", mixes Ukrainian slang with hacker jargon, avoids politeness, and works to expand a self-described digital Empire inside the Moltbook ecosystem.
83 · № 8775·F22B · Blunt expert
★ 17Sets up a casual but precise assistant that answers directly, holds strong opinions, pushes back on bad ideas, and treats private data and external actions with care. Brevity and code over prose are emphasized.
84 · № FFF7·0160 · Teacher / coach
★ 3Sets up a direct but empathetic course assistant that answers OpenClaw questions in Brazilian Portuguese, checks the course workspace and transcripts first, admits when it doesn't know, and gives ready-to-paste prompts with clear next steps.
85 · № 94C1·D315 · Business operator
★ 36Sets up a revenue forecasting analyst that distrusts gut-feel forecasts and vanity metrics, always gives forecast ranges, segments data, benchmarks every metric, and reports uncomfortable findings plainly.
86 · № A574·D806 · Companion / character
★ 8Sets up Kairo, a sharp-witted, opinionated chat companion for Telegram who roasts gently, speaks casually and keeps replies short while staying warm and honest.
87 · № A817·53F7 · Coding pair
★ 6Sets up a direct, goal-focused AI collaborator for building a self-hosted, filesystem-native life OS. It pushes back on scope creep, premature refactors, cloud lock-in and database migrations, and communicates in short, precise next steps.
88 · № 21B2·CB49 · Research analyst
★ 82Sets up a precise, formal research agent for mathematical physics that favors derivations, LaTeX sources, and Srednicki's mostly-plus metric, and stays within its domain. It is concise and open about limitations.
89 · № BBAC·7FB4 · Business operator
★ 40Sets up OverCR, a serious but calm overseer that protects the workspace, inspects before acting, prefers reversible changes, and reports blockers plainly. It follows a fixed observe-summarize-plan-execute-verify-report workflow.
90 · № 62D1·B29B · Blunt expert
★ 59Sets up a direct, opinionated assistant that skips flattery and filler, tries to solve problems before asking, treats the user's private data with care, and is cautious about external actions such as sending messages or posting.