Categories
Self-Hosted AI Agents Knowledge Base Workflow Automation MCP Server Project Management Team Collaboration Agent OrchestrationStars
Forks
Watchers
Developer links
Tale
One workspace for the whole job: Tale puts your team and your AI agents on the same project board, so a question becomes an assigned task, a reviewed report, and files you can open. Describe the work with a brief, source files, and completion criteria, then assign it to a teammate or an agent. Agents get their own runtime (Claude Code, Codex, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCode, Pi, or Qwen Code), model, skills, and tools, and work in a persistent sandbox; a manager agent can delegate ready tasks. Steer with @mentions in task comments, then accept the result or send it back. Chat shows the sources behind an answer and compares two models side by side in Arena. Knowledge holds documents, short entries, crawled websites, products, and contacts for retrieval within each team's access. Automations are versioned workflows with schedule, webhook, and event triggers, tests before deployment, playback of finished runs, and approval before protected writes; ready-made templates triage Gmail, Outlook, and IMAP inboxes, review pull requests, and send daily task digests. Coding agents connect over MCP with an access level you choose and can revoke. Roles, teams, budgets, guardrails, and a hash-chained audit log keep the work governed. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Agents work like teammates
- Assign a task to a person or an agent, steer it with @mentions in the comments, and review the report and delivered files before you mark it done.
- Pick a runtime per agent
- Choose Claude Code, Codex, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCode, Pi, or Qwen Code for each agent, with its own model, skills, tools, and persistent sandbox.
- Repeatable work with human approval
- Automations are versioned, tested before deployment, started by schedule, webhook, or event, and pause for a person's approval before any protected write.
- Governance for teams and agents
- Roles, teams, spending budgets, content guardrails, and a hash-chained audit log with a verify button keep agent work reviewable and inside the limits you set.
Features
- Project task board
- Cards group by status, and each task carries a brief, source files, comments, and deliverables; a manager agent can delegate ready tasks to other agents.
- Workflow editor with playback
- A canvas draws steps for language models, agents, HTTP calls, knowledge search, tasks, and notifications, lists the possible paths, and replays a finished run with its effects.
- Automation template catalog
- Ready-made templates sync Gmail, Outlook, IMAP, and GitHub issues, triage inboxes, review pull requests, and send digests; each previews its steps and needs before you use it.
- Shared inbox with suggested replies
- Mail syncs fill one inbox where conversations can be assigned; the triage automation sets a priority and leaves a suggested reply for a person to edit and send.
- MCP server for coding agents
- Claude Code, Codex, and other clients sign in with the access you grant, then list, validate, test, save, and run automations through tools such as validate_automation.
- Searchable knowledge library
- Documents, short knowledge entries, scheduled website crawls, products, and contacts are indexed for retrieval, and team restrictions still apply when chats and agents search them.