whereismyai
Distilly
Distilly is an agent person-modeling layer that turns source materials into a reusable Person Profile for AI agents.
Distilly is the person-modeling layer for agents that turns source materials into a portable, source-grounded Person Profile built from observable experience, decision patterns, expression, and ways of working. It supports three character families: colleagues, relationships, and celebrities, using family-specific source collection strategies, analysis dimensions, and profile structures. Users can input data through Lark, DingTalk, Slack, Public X posts, WeChat chat history, PDF, images, screenshots, Lark JSON export, email .eml or .mbox, and markdown or direct paste. Each generated Person Profile is packaged as an Agent Skill and can be installed into supported local agent hosts. The tool also features delta file appending, conversation correction, version control, and a celebrity research pipeline.
Distilly at a glance
- Best for: Founder, HR, Software engineer
- Runs on: Web, API, CLI
- Pricing: Free
- Released: March 2026
- Category: AI agent tool
- Website: github.com/titanwings/distilly
Key features
- Generate source-grounded Person Profiles for agents
- Support colleague, relationship, and celebrity person families
- Ingest Lark, DingTalk, Slack, WeChat, and file uploads
- Package profiles as installable Agent Skills
- Append delta files and auto-analyze updates
- Apply conversation corrections to profile layers
- Auto-archive profile versions and allow rollbacks
- Run a six-dimension celebrity research pipeline
Use it for
- Distill a departed colleague into a reusable work skill
- Capture expression patterns and emotional triggers for personal relationships
- Model public figures, creators, or fictional characters
- Create custom AI agents that respond using a specific person's judgment and voice
Alternatives to Distilly
- Dify — Open-source visual builder for agents and RAG apps
- Distilabel — Build scalable, research-backed pipelines for synthetic data and AI feedback.
- LLMStack — Builds AI applications and agents with custom data without writing code.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Pipedream — Managed authentication and 10,000+ tools for connecting AI agents to APIs.
- BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
- Alook — Connects existing local coding agents to team communication channels.
- Cykel — Automates complex business tasks 24/7 using autonomous AI agents.
- Adyen — Share AI agent resources across coding tools and repositories easily.
- Clai — Query twelve models and local Ollama directly from your terminal using unix pipes.
- CowAgent — Open-source agent with multi-model and multi-channel support.
- Acontext — Builds human-readable Markdown skill files from agent runs without using embeddings.
All Distilly alternatives