Deploy Now

Stars

5,001

Forks

371

Watchers

46

Developer links

EvoScientist

EvoScientist gives a research project a team of cooperating AI agents that plan experiments, read papers, write and debug code, and draft reports, then remember what they learned so the next project starts further ahead. A researcher can schedule a weekday arXiv digest as a cron-style task, optionally graded against a rubric checklist, while a lab lead reviews the reusable skills that AutoSkills proposes from recurring patterns. The EvoSkills catalog adds ready-made skills such as academic slides, paper figures, and experiment pipelines. Six sub-agents cover planning, research, coding, debugging, data analysis, and writing, following a workflow of intake, plan, execute, evaluate, write, and verify. Each turn is distilled into a memory that links itself into a knowledge graph you can browse in the EvoMemory view, next to profile pages for you, your research taste, and the agent's SOUL. Work from a terminal UI, a browser workspace with a file tree and agent panel, or messaging channels including Telegram, Slack, and Feishu that share one session. Rubric and goal commands grade each turn against acceptance criteria you approve. MCP servers plug in extra tools with one command, shell commands ask for approval by default, and the Docker image confines file edits to the folders you mount. Choose Anthropic, OpenAI, Google, MiniMax, NVIDIA, or any OpenAI-compatible endpoint such as vLLM. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

EvoScientist
EvoScientist
EvoScientist
EvoScientist
EvoScientist
EvoScientist

Benefits

  • Agents That Remember Your Research
  • Every turn is distilled into memory and linked into a knowledge graph, so your preferences, lessons, and findings carry across sessions instead of vanishing when a chat ends.
  • Work From Browser, Terminal, Chat
  • Use the terminal UI, the browser workspace, or messaging apps such as Telegram and Slack. All share one agent session, so you can check on a long run from your phone.
  • Review Before Anything Runs
  • Shell commands need your approval by default, an allow-list can permit trusted command prefixes, and the Docker image keeps file edits inside mounted folders, so autonomy stays supervised.
  • Bring Any Model Provider
  • One config switches between Anthropic, OpenAI, Google, MiniMax, and NVIDIA, and custom endpoints such as vLLM or LM Studio also work, so you are never locked to one vendor.

Features

  • Six-Agent Research Team
  • Specialist sub-agents for planning, research, coding, debugging, analysis, and writing follow an intake, plan, execute, evaluate, write, and verify workflow for end-to-end research projects.
  • EvoMemory Knowledge Graph
  • Browse Identity, Knowledge, and History tabs: profile pages, a node-and-edge graph of semantic and procedural memories, and relations such as Complements between linked notes.
  • Skills And AutoSkills
  • Install skills from the EvoSkills catalog or GitHub, and let AutoSkills propose new ones distilled from recurring patterns in memory, ready for you to approve with /autoskills.
  • Scheduled Research Tasks
  • Add cron-expression schedules with /schedule, optionally with a rubric checklist that a separate reviewer grades, then pause, resume, or run each schedule on demand.
  • MCP And Channel Integrations
  • Add MCP servers with EvoSci mcp add, and run Telegram, Slack, Feishu, QQ, WeChat, or iMessage channels concurrently against the same agent session.
  • Browser Workspace UI
  • Start it with EvoSci --ui webui for a chat view, a workspace file tree, an Agents panel showing running sub-agents, a skills catalog, and EvoMemory pages.

Apps Similar to EvoScientist