mimicry 0.4 / private alpha

an agent that runs your conversations.

mimicry lives inside a real telegram client. it handles the work in the background. nothing reaches another person until you approve it.

ingress
excluded chats never enter the system
brains
reasoning and memory stay on your machine
egress
every outgoing message waits for your tap
cross the horizon

give it the outcome.

01 / intent

say what needs to happen once. use the same language you would use with a person.

02 / context

mimicry finds the people, opens only the context it needs, and carries the task between steps.

03 / veto

the work can move. the final message cannot. every send waits at a boundary you control.

task / 0048live local run
move friday's sync to 16:00. tell the team and follow up with anyone who misses it.
project chatlast scheduling thread4 recipients
01found4 people in the project chat
02readthe last scheduling thread
03drafted4 context-aware messages
ready to send4 messages / nothing sent yet
M / 04
inside the perimeter

the work stays visible.

0.4 makes the invisible parts inspectable: what enters the model, who owns the running job, and exactly where action stops.

one agent. selected context. one explicit boundary between thinking and acting.

01 / context

see the budget

preview what enters the model and how much room remains before the request starts.

02 / continuity

leave. come back.

jobs stay owned by the local server while the client changes accounts or views.

03 / boundary

you remain the edge

the agent can prepare the work. the outgoing path remains blocked until you approve it.

trust is not the feature.

verification is. excluded chats are never collected. the brains run on your machine. prompts go directly to the AI provider you choose, so that provider sees what you send it. mimicry's cloud holds keys and billing. it never receives your chats.

ingress
read the open filter
brains
watch the provider-direct path
egress
verify the approval gate
inspect the source