Personal agent: from chat to real tools
A personal assistant configured on an open-source agent runtime: messaging, memory files, tools and scheduled tasks, including the limitations exposed by actual use.
What was built?
The work was the agent’s operating environment and behaviour, not a new language model or a runtime built from scratch. The setup connected one allow-listed user’s messaging channel, a local container, persistent memory files, and browser, terminal and file tools. Recurring activities became scheduled jobs. Persona, instructions and skills shaped how tools were used.
Workflow and review boundary
Message
The user gives a task through the allowed messaging channel.
Context
The agent uses instructions and local memory files. Persistent files do not guarantee that every earlier detail will be retrieved when needed.
Tool use
A task may require reading a page, changing a file or executing a command. Tool availability and successful task completion are different things.
Review
External actions require a distinction between preparation and approval. The boundary shown here is an operating requirement, not proof of a technical safeguard that blocks every action.
Result
An answer or file becomes an inspectable result. For scheduled work, inspect the latest run rather than merely checking that the job is enabled.
What operation revealed
Provider balance is part of reliability.
One scheduled task stopped when the external model account ran out of funds. The local server remained online, but the task did not finish. A resolution had not been retested in the source review.
A symlink does not resolve an access boundary.
Two scripts sat outside the scheduler’s permitted directory. A symlink workaround failed because the guard resolved the actual path. The jobs remained broken at review time.
Configured does not mean connected.
Some additional channels and services appeared in configuration but were not operational. They cannot be described as delivered integrations.
My contribution
I defined the assistant’s role, tools and everyday use, and operated the installation. AI helped with instructions, skills and scripts. The underlying runtime is third-party open-source software.
Data boundaries
Files and tools were local, but conversation content and context went to an external model service. Telegram is also external. Local hosting does not mean entirely local processing.