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

16
doc/dmn-algorithms.md
View file

@ -26,18 +26,18 @@ half_life = 7 days
A goal worked on today scores 1.0. A goal untouched for a week
scores 0.37. A goal untouched for a month scores 0.02.
**mention**: Boost when Kent recently mentioned it. Decays fast.
**mention**: Boost when the user recently mentioned it. Decays fast.
```
mention = 1.0 + (2.0 × exp(-hours_since_mention / 24))
```
A goal Kent mentioned today gets a 3x multiplier. After 24h, the
A goal the user mentioned today gets a 3x multiplier. After 24h, the
boost has decayed to 1.74x. After 48h, 1.27x. After a week, ~1.0.
**tractability**: Subjective estimate (0.0-1.0) of how much autonomous
progress is possible without Kent. Set manually per goal.
progress is possible without the user. Set manually per goal.
- 1.0: I can do this independently (code polish, research, reading)
- 0.5: I can make progress but may need review (moderate features)
- 0.2: Needs Kent's input (kernel changes, design decisions)
- 0.2: Needs the user's input (kernel changes, design decisions)
- 0.0: Blocked (waiting on external dependency)
**connections**: How many other active goals share links with this one.
@ -57,7 +57,7 @@ explicit and consistent, not that it's automated.
### When to recompute
- At session start (orient phase)
- When Kent mentions a goal
- When the user mentions a goal
- After completing a task (adjacent goals may shift)
## 2. Associative Replay Scheduling
@ -163,7 +163,7 @@ When stuck:
- Minimum incubation: 1 session (don't come back to it in the same
session you got stuck)
- Maximum incubation: 5 sessions. After that, escalate: ask Kent,
- Maximum incubation: 5 sessions. After that, escalate: ask the user,
try a radically different approach, or deprioritize the goal.
## 4. Consolidation Triggers
@ -174,7 +174,7 @@ prompts.
### Primary signal: scratch.md length
Kent's idea: scratch.md getting long is a natural pressure signal.
the user's idea: scratch.md getting long is a natural pressure signal.
```
consolidation_pressure(scratch) = lines(scratch) / threshold
@ -268,7 +268,7 @@ The cycle is self-regulating:
| Parameter | Current | Watch for |
|-----------|---------|-----------|
| recency half_life | 7 days | Goals decaying too fast/slow |
| mention boost | 3x → 1x over 24h | Kent's priorities properly reflected? |
| mention boost | 3x → 1x over 24h | the user's priorities properly reflected? |
| replay k | 3 episodes × 5 goals | Too many? Too few? |
| stuck threshold | 3 sessions | Catching real stuckness? |
| max incubation | 5 sessions | Is this enough? |