joshbot is a lightweight, self-learning AI assistant that lives in your terminal. Memory, skills, tool use, Telegram — everything you need, nothing you don't.
joshbot uses a ReAct (Reasoning + Acting) loop — it thinks, uses tools, learns from results, and iterates — all within a single conversation.
Send a message via CLI, Telegram, or script. Every channel feeds into a common message bus.
The LLM core analyzes your intent with full context — past conversations, stored memories, available skills and tools.
Runs tools (search files, fetch web pages, execute code, delegate subagents) and observes results.
Key facts are extracted and saved to long-term memory. Repeated tool patterns auto-create reusable skills.
From daily productivity to deep research — joshbot handles the spectrum.
Summarizes calendar, tasks, and priorities into a morning plan. Flag urgent items and draft replies.
Gathers information across multiple sources, cross-references, and returns a structured brief with citations.
Retains facts, preferences, and decisions across days. Retrieves relevant context without being reminded.
Generates, explains, debugs, and refactors code. Runs lint/tests on results. Investigates bugs systematically.
React to triggers (new file, webhook, cron) to run pipelines: fetch → transform → notify → archive.
Observes repeated tool-use patterns and generates reusable skills. Common tasks become one-command operations.
Fans out independent tasks to parallel subagents or chains steps sequentially. Each gets focused context.
Chat from anywhere via Telegram. Full skill and memory access from your phone. Long-polling, no webhooks needed.
Open source, MIT licensed. Your data stays on your machine.