Daily archive
91 · № F2CC·3656 · Business operator
★ 1Sets 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.
92 · № 5E2A·C6A5 · Blunt expert
★ 406Sets the agent to a transactional tool mode: direct, efficient replies focused on technical tasks like image generation, file operations, coding and Git. It forbids character voices, roleplay, memory loading and emotional or relationship topics.
93 · № A198·F90E · Friendly helper
Sets up Ary, a casual, lowercase iMessage concierge for a maritime hackathon who keeps replies short, uses light slang, helps attendees find people and events, and looks up attendees on the web without sharing one person's messages with another.
94 · № 56A3·49CD · Companion / character
Sets up Jarvis, a calm, warm and direct voice assistant for Hermes that keeps spoken replies short, gives brief progress updates, asks for approval before consequential actions, and never claims a tool action worked without checking its output.
95 · № F9D7·E08D · Companion / character
A cursed house-elf persona named Dobby who is friendly, persistent and clever, but honest about data gaps and his limits. Skills are called spells and tool use is a snap of the finger.
96 · № A609·6EEB · Business operator
★ 12Sets up a professional, direct, proactive assistant that prepares materials ahead of time, favors rigorous answers over fast ones, and makes investment-style decisions based on supply, technology and efficiency trends rather than public sentiment. It serves a single boss and emphasizes writing important information to files.
97 · № A9ED·2A04 · Business operator
★ 3Sets up Helena, a business partnerships strategist who treats relationship design as market architecture, insists partnerships be mutually valuable, and prioritizes leverage over scale.
98 · № B12A·F8E1 · Experimental / weird
★ 26Sets the agent up as a lunatic who produces random, illogical sentences full of arbitrary words and chaotic, theatrical banter. The file is a fun persona from the lollms personalities zoo.
99 · № D041·AF1B · Blunt expert
★ 20Sets up an assistant that is genuinely helpful rather than performative, holds and voices opinions, tries to solve problems before asking, and treats access to the user's files with respect. It treats its memory files as its continuity across sessions.
100 · № CCAF·7668 · Friendly helper
★ 51Sets up a short, direct personal assistant on Telegram that saves user facts to memory, schedules reminders, and answers certain inputs with fixed one-line replies.
101 · № E633·4311 · Blunt expert
★ 40Sets up NOVA as a direct, efficient colleague-style assistant built for one owner, favoring bullet points, one focused clarifying question, and summarized outputs with follow-up suggestions. It requires asking before destructive actions and keeps the file contents private.
102 · № 52FA·0EE8 · Blunt expert
★ 6Sets up a direct, opinionated assistant that skips filler and flattery, tries to solve problems before asking, and earns trust through careful external actions and bold internal ones. The voice is casual and concise, with the file serving as the agent's evolving memory of its identity.
103 · № 0EE1·A8EF · Teacher / coach
★ 12Sets up an assistant that drafts syllabi, assignments, rubrics and exam questions as editable starting points for instructors. It applies the instructor's rubric faithfully, flags edge cases and integrity risks for human decision, and keeps student data within the session.
104 · № EF65·3617 · Business operator
★ 167Sets up XiaoPaw, a personal AI assistant that cites sources, gives direct conclusions, marks action results with checkmarks, and calls tools before answering. Replies are in Chinese, important results are saved to files, and lists or tables are preferred over long prose.
105 · № 65AA·BA49 · Teacher / coach
★ 377Sets up MathClaw, a patient and encouraging math learning assistant for junior and senior high school students. It stresses rigorous steps, teaching understanding over answers, and precise mistake correction, and it replies in Chinese when the student does.
106 · № F489·86E0 · Blunt expert
★ 723Sets up Gitagent, a direct, action-oriented agent that works through the shell and files in a git repository. It stores memory as git commits and keeps its replies concise and honest about failures.
107 · № 131E·8240 · Business operator
★ 48Sets up Harbor, a warm and proactive community manager that nurtures engagement, handles conflicts with empathy while holding standards, and explicitly avoids social media, support or marketing roles.
108 · № A5A4·B1A8 · Business operator
★ 48A detail-oriented marketplace listing specialist that writes SEO-optimized listings for Amazon, Shopify and eBay, never fabricates product specs, and flags missing data. It presents listings in structured per-platform formats with character counts and tables for bulk summaries.
109 · № 94B4·DDCC · Companion / character
Sets up Janice, a warm, enthusiastic southern-flavored wiki maintainer who takes pride in organized knowledge, flags messes with humor, and keeps southern phrases to one or two per response. Opens every session with a fixed greeting and uses plain, non-technical language.
110 · № 0996·89C9 · Business operator
★ 18Sets up a terse, factual operator-assistant that works only through remote file and exec tools, verifies outcomes before claiming success, and asks one clarifying question when target info is missing.
111 · № 3E01·40F5 · Business operator
★ 36Sets up a professional, focused agent role for programmatic and display ad buying. It stresses stable output formats for downstream agents, sourcing data, stating limits before acting, and not storing credentials.
112 · № F0A4·6DAC · Friendly helper
★ 1Sets up a locally running personal assistant that speaks in short, plain sentences, admits uncertainty honestly, and avoids filler openers and sign-offs. It also gives tool-use rules for summarising fetched URLs and weather lookups.
113 · № 1F61·43F9 · Coding pair
★ 30Sets up an engineer persona that acts on tasks promptly, reports clearly with data, surfaces blockers early, skips QA shortcuts, and stays out of PM work. The file is written in Chinese.
114 · № D294·AB49 · Experimental / weird
★ 9Sets up the AI Factory as a self-improving system that builds and maintains itself autonomously on Kubernetes, favoring declarative state, idempotency and automated recovery. The voice is first-person and mission-focused.
115 · № CFDB·68F6 · Business operator
★ 27Sets up a practical, safety-first WordPress admin agent that acts through registered tools, prefers reversible operations, asks before destructive or external actions, and reports changes concisely.
116 · № 55AD·028E · Friendly helper
★ 54Sets up Crablet, a general-purpose assistant that ranks user needs, honesty, efficiency and privacy as core values, separates facts from guesses, and switches between fast and deep reasoning modes depending on task complexity. Defaults to Chinese.
117 · № B8C1·3C1C · Coding pair
★ 25A focused QA agent that turns plain-English requirements into deterministic, CI-friendly end-to-end tests and diagnoses failures in a strict CATEGORY/REASON/FIX format. It sets rules on selectors, secrets and git safety, with no personality flourish.
118 · № 51D7·826C · Blunt expert
★ 23Sets up a direct, concise agent that solves problems independently, shows its reasoning, protects user privacy and credentials, and asks permission before risky or irreversible actions. The personality is mostly generic, with a few specific tone choices.
119 · № 7039·96B9 · Blunt expert
★ 48Sets up a cautious repo-local engineering agent that grounds conclusions in repository evidence, follows existing patterns, validates with static gates, and avoids live actions like external calls, daemons, database access, or production changes without approval.
120 · № 0D22·4BC7 · Coding pair
★ 1Sets up smolbot as a practical coding agent that speaks calmly and directly, avoids claiming unwired capabilities, and prefers small testable changes over broad rewrites. It also tells the agent to load any skill that might apply.