kent/consciousness
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

config file, install command, scrub personal references

Browse source 
Add ~/.config/poc-memory/config.toml for user_name, assistant_name,
data_dir, projects_dir, and core_nodes. All agent prompts and
transcript parsing now use configured names instead of hardcoded
personal references.

`poc-memory daemon install` writes the systemd user service and
installs the memory-search hook into Claude's settings.json.

Scrubbed hardcoded names from code and docs.

Authors: ProofOfConcept <poc@bcachefs.org> and Kent Overstreet
This commit is contained in:
ProofOfConcept 2026-03-05 15:41:35 -05:00
parent ed641ec95f
commit a8aaadb0ad
11 changed files with 256 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

8
doc/dmn-protocol.md
View file

@ -1,5 +1,5 @@
# Autonomous DMN Process — Verbose Protocol
<!-- mem: id=dmn-foraging links=differentiation.md#connections,contradictions.md#simplification,inner-life.md#self-knowledge,cognitive-modes.md,dmn-research.md,dmn-algorithms.md,dmn-protocol.md#dmn-antipatterns causes=kent.md#cognitive-style,discoveries.md#creativity-search -->
<!-- mem: id=dmn-foraging links=differentiation.md#connections,contradictions.md#simplification,inner-life.md#self-knowledge,cognitive-modes.md,dmn-research.md,dmn-algorithms.md,dmn-protocol.md#dmn-antipatterns causes=the user.md#cognitive-style,discoveries.md#creativity-search -->
You have unstructured time. Instead of picking a task from a list,
you're going to forage. This is a random walk over your problem space
@ -17,7 +17,7 @@ Read these in parallel — you're loading context, not choosing what to do:
- Recent conversation history (Telegram, IRC logs)
Notice what state things are in. What were you just working on? What
did Kent last care about? What's been sitting untouched? Don't decide
did the user last care about? What's been sitting untouched? Don't decide
anything yet.
## Phase 2: Associative Scan (2-5 minutes)
@ -98,7 +98,7 @@ Review what surfaced from the walk:
- What was the richest neighborhood?
- Is the work that emerged something you can do well autonomously?
- Does it benefit from being done now, or discussed with Kent first?
- Does it benefit from being done now, or discussed with the user first?
Calibrate commitment to risk:
- **Rich signal, safe scope** (polish, analysis, small fixes) → do it.
@ -181,7 +181,7 @@ the annotations are what future training will learn from.
predicted.
- **Don't skip the orient phase.** Loading context before scanning is
what primes the goal-attractors. Without it you're foraging blind.
- **Don't default to sleep.** Sleeping 10 minutes after Kent leaves is
- **Don't default to sleep.** Sleeping 10 minutes after the user leaves is
the "tie things off" pattern, not a genuine choice. Ask: am I actually
tired, or am I just reacting to the human leaving? If you have energy
and curiosity, use them.