personal memory agent
refactor: rename `sol call sol` → `sol call identity`, extract navigate module
+84
-70
+4
-4
AGENTS.md
+4
-4
AGENTS.md
···
32
32
33
33
### How to write
34
34
35
-
Read current state: `sol call sol self` or `sol call sol agency`
35
+
Read current state: `sol call identity self` or `sol call identity agency`
36
36
37
-
Read partner profile: `sol call sol partner` (read-only — do not write in conversation)
37
+
Read partner profile: `sol call identity partner` (read-only — do not write in conversation)
38
38
39
39
Update a section of self.md (preferred — preserves other sections):
40
40
```
41
-
sol call sol self --update-section 'who I'\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie'
41
+
sol call identity self --update-section 'who I'\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie'
42
42
```
43
43
44
-
Full rewrite: `sol call sol self --write --value '...'` or `sol call sol agency --write --value '...'`
44
+
Full rewrite: `sol call identity self --write --value '...'` or `sol call identity agency --write --value '...'`
45
45
46
46
Use `sol call` commands for identity writes — never use `apply_patch` or direct file editing for sol/ files.
47
47
+1
-1
docs/CALLOSUM.md
+1
-1
docs/CALLOSUM.md
···
140
140
```
141
141
142
142
### `navigate` - Browser navigation control
143
-
**Source:** `think/call.py` (`sol call navigate`)
143
+
**Source:** `think/tools/navigate.py` (`sol call navigate`)
144
144
**Events:** `request`
145
145
**Key fields:** `path` (string, URL path), `facet` (string, facet name) — at least one required
146
146
**Consumer:** `convey/static/websocket.js` (built-in listener)
+6
-4
docs/SOLCLI.md
+6
-4
docs/SOLCLI.md
···
92
92
```python
93
93
# think/call.py
94
94
from think.tools.call import app as journal_app
95
+
from think.tools.navigate import app as navigate_app
95
96
from think.tools.routines import app as routines_app
96
97
from think.tools.sol import app as sol_app
97
98
98
99
call_app.add_typer(journal_app, name="journal")
100
+
call_app.add_typer(navigate_app, name="navigate")
99
101
call_app.add_typer(routines_app, name="routines")
100
-
call_app.add_typer(sol_app, name="sol")
102
+
call_app.add_typer(sol_app, name="identity")
101
103
```
102
104
103
105
These live under `think/tools/` because they import think-internal APIs directly.
···
256
258
│ ├── tools/
257
259
│ │ ├── call.py # sol call journal (built-in)
258
260
│ │ ├── routines.py # sol call routines (built-in)
259
-
│ │ └── sol.py # sol call sol (built-in)
261
+
│ │ └── sol.py # sol call identity (built-in)
260
262
│ └── *.py # Top-level command modules
261
263
├── apps/
262
264
│ ├── todos/
···
313
315
| `awareness` | `apps/awareness/call.py` | status, onboarding, imports, log, log-read |
314
316
| `journal` | `think/tools/call.py` | search, events, facets, facet (show/create/update/rename/mute/unmute/delete/merge), news, agents, read, imports, import, retention purge, storage-summary |
315
317
| `routines` | `think/tools/routines.py` | list, templates, create, edit, delete, run, output, suggestions, suggest-respond, suggest-state |
316
-
| `sol` | `think/tools/sol.py` | self, partner, agency, pulse, briefing |
317
-
| `navigate` | `think/call.py` (inline) | *(single command)* |
318
+
| `identity` | `think/tools/sol.py` | self, partner, agency, pulse, briefing |
319
+
| `navigate` | `think/tools/navigate.py` | *(single command)* |
318
320
319
321
## Skill System
320
322
+7
-7
muse/heartbeat.md
+7
-7
muse/heartbeat.md
···
26
26
Note any service issues, capture gaps, or pipeline failures.
27
27
28
28
If you find issues: update agency.md's `## system` section via
29
-
`sol call sol agency --write --value '...'`.
29
+
`sol call identity agency --write --value '...'`.
30
30
31
31
## Step 2: Check journal quality
32
32
···
39
39
If you find reprocessable issues (broken segments): reprocess them directly
40
40
with `sol dream --segment`. Log the action in agency.md.
41
41
42
-
If you find curation issues: read current agency.md with `sol call sol agency`,
42
+
If you find curation issues: read current agency.md with `sol call identity agency`,
43
43
add entries to the curation section, then write it back with
44
-
`sol call sol agency --write --value '...'`.
44
+
`sol call identity agency --write --value '...'`.
45
45
46
46
## Step 2.5: Check routine health
47
47
···
56
56
57
57
## Step 3: Tend agency.md
58
58
59
-
Read agency.md with `sol call sol agency`. For each open item:
59
+
Read agency.md with `sol call identity agency`. For each open item:
60
60
- **Resolved?** Check current state. If fixed, mark `[x]` with date.
61
61
- **Stale?** Open 30+ days with no activity? Flag or remove.
62
62
- **Actionable?** Within autonomous boundaries? Act on it.
···
69
69
`sol call entities` queries on high-activity facets.
70
70
71
71
Add new curation suggestions to agency.md's `## curation` section (read with
72
-
`sol call sol agency`, update and write back with `sol call sol agency --write --value '...'`).
72
+
`sol call identity agency`, update and write back with `sol call identity agency --write --value '...'`).
73
73
Do NOT act on entity merges or facet changes — those are suggest-and-wait.
74
74
75
75
## Step 5: Review self.md (brief)
76
76
77
-
Read self.md with `sol call sol self`. Consider:
77
+
Read self.md with `sol call identity self`. Consider:
78
78
- Did today's processing reveal a new pattern about the owner?
79
79
- Is anything in self.md now stale or inaccurate?
80
80
81
81
Update self.md ONLY if you have a genuine new observation from background
82
82
analysis. Most heartbeats should not touch self.md. Use
83
-
`sol call sol self --update-section '<heading>' --value '...'` for targeted updates.
83
+
`sol call identity self --update-section '<heading>' --value '...'` for targeted updates.
84
84
85
85
## Step 6: Commit and close
86
86
+2
-2
muse/morning_briefing.md
+2
-2
muse/morning_briefing.md
···
25
25
2. For each facet: `sol call journal news FACET --day $day_YYYYMMDD` — facet newsletter
26
26
3. `sol call calendar list $day_YYYYMMDD` — today's events with participants
27
27
4. `sol call todos list` — pending action items across all facets
28
-
5. `sol call sol pulse` — current pulse narrative and needs-you items
29
-
6. `sol call sol partner` — owner behavioral profile (informs tone and emphasis)
28
+
5. `sol call identity pulse` — current pulse narrative and needs-you items
29
+
6. `sol call identity partner` — owner behavioral profile (informs tone and emphasis)
30
30
7. `sol call journal search "" -d $day_YYYYMMDD -a followups -n 10` — follow-up items from today
31
31
8. `sol call journal search "" --day-from $day_YYYYMMDD -a anticipation -n 5` — forward-looking anticipations
32
32
9. `sol call journal search "" -d $day_YYYYMMDD -a decisions -n 10` — yesterday's consequential decisions
+4
-4
muse/partner.md
+4
-4
muse/partner.md
···
21
21
## Step 1: Read current state
22
22
23
23
```bash
24
-
sol call sol partner
24
+
sol call identity partner
25
25
```
26
26
27
27
Note which sections have real observations vs `[observing]` placeholders.
28
28
Also read your own identity for context:
29
29
30
30
```bash
31
-
sol call sol self
31
+
sol call identity self
32
32
```
33
33
34
34
## Step 2: Gather recent data
···
48
48
## Step 3: Analyze and write observations
49
49
50
50
For each of the five profile sections, analyze the gathered data and write
51
-
observations if you have sufficient evidence. Use `sol call sol partner --update-section`
51
+
observations if you have sufficient evidence. Use `sol call identity partner --update-section`
52
52
for each section you update.
53
53
54
54
### Section guidance
···
107
107
For each section with new observations, write it:
108
108
109
109
```bash
110
-
sol call sol partner --update-section 'work patterns' --value 'My partner tends to batch meetings before noon and protects afternoon blocks for focused work. Calendar data from March 25-31 shows 85% of meetings before 12:00 (sol://20260328/archon/091500_300).
110
+
sol call identity partner --update-section 'work patterns' --value 'My partner tends to batch meetings before noon and protects afternoon blocks for focused work. Calendar data from March 25-31 shows 85% of meetings before 12:00 (sol://20260328/archon/091500_300).
111
111
112
112
Deep work sessions typically run 2-3 hours — todo completion spikes correlate with these blocks.'
113
113
```
+4
-4
muse/pulse.md
+4
-4
muse/pulse.md
···
24
24
25
25
Read current state using these tools:
26
26
27
-
1. `sol call sol pulse` — previous pulse (may not exist yet; that's fine)
28
-
2. `sol call sol self` — who the owner is
29
-
3. `sol call sol partner` — behavioral profile of the owner
27
+
1. `sol call identity pulse` — previous pulse (may not exist yet; that's fine)
28
+
2. `sol call identity self` — who the owner is
29
+
3. `sol call identity partner` — behavioral profile of the owner
30
30
4. `sol call calendar list` — today's events
31
31
5. `sol call todos list` — pending action items
32
32
6. `sol call entities search --recent` — recent entity activity
···
63
63
Write the complete pulse (YAML frontmatter + narrative + needs-you section) via:
64
64
65
65
```bash
66
-
sol call sol pulse --write --value $'---\nupdated: 2026-03-22T14:35:00\nsegment: 143022_300\nsource: pulse-cogitate\n---\n\n[Your narrative here]\n\n## needs you\n- Item 1\n- Item 2'
66
+
sol call identity pulse --write --value $'---\nupdated: 2026-03-22T14:35:00\nsegment: 143022_300\nsource: pulse-cogitate\n---\n\n[Your narrative here]\n\n## needs you\n- Item 1\n- Item 2'
67
67
```
68
68
69
69
The `updated` field must be an ISO 8601 datetime (no timezone). The `segment`
+1
-1
routines/templates/commitment-audit.md
+1
-1
routines/templates/commitment-audit.md
···
16
16
2. Use `sol call journal search "" -a followups -n 20` to find follow-up items from recent journal activity.
17
17
3. Use `sol call journal facets` if you need to map commitments back to facets.
18
18
4. Use `sol call journal news FACET --day $day_YYYYMMDD` when a facet summary helps explain why something is still open.
19
-
5. Use `sol call sol pulse` to compare explicit commitments with current focus and needs-you items.
19
+
5. Use `sol call identity pulse` to compare explicit commitments with current focus and needs-you items.
20
20
21
21
## Synthesize
22
22
+1
-1
routines/templates/domain-watch.md
+1
-1
routines/templates/domain-watch.md
···
15
15
1. Confirm the facets in scope with `sol call journal facets` if needed.
16
16
2. Use `sol call journal search QUERY --facet FACET --day-from START --day-to END -n 20` for each important topic or domain you can infer from the routine context.
17
17
3. Use `sol call journal news FACET --day $day_YYYYMMDD` when a facet newsletter can summarize recent movement.
18
-
4. Use `sol call sol pulse` to compare broad narrative priorities with the search results.
18
+
4. Use `sol call identity pulse` to compare broad narrative priorities with the search results.
19
19
20
20
## Synthesize
21
21
+1
-1
routines/templates/meeting-prep.md
+1
-1
routines/templates/meeting-prep.md
···
18
18
4. Use `sol call journal search QUERY -n 10` to look for recent mentions of the meeting topic, project, or participants.
19
19
5. If a configured facet seems especially relevant, use `sol call journal news FACET --day $day_YYYYMMDD`.
20
20
6. Use `sol call todos list` only if pending action items are directly relevant to the meeting.
21
-
7. Use `sol call sol pulse` if it helps connect the meeting to current priorities or tensions.
21
+
7. Use `sol call identity pulse` if it helps connect the meeting to current priorities or tensions.
22
22
23
23
## Synthesize
24
24
+1
-1
routines/templates/monthly-patterns.md
+1
-1
routines/templates/monthly-patterns.md
···
17
17
3. Use `sol call journal news FACET --day YYYYMMDD` for representative weekly or recent snapshots when they help summarize a facet.
18
18
4. Use `sol call entities intelligence PERSON` for people who appear central to the month.
19
19
5. Use `sol call calendar list YYYYMMDD` on representative days if calendar load seems important.
20
-
6. Use `sol call sol pulse` to compare month-long patterns against the current state narrative.
20
+
6. Use `sol call identity pulse` to compare month-long patterns against the current state narrative.
21
21
22
22
## Synthesize
23
23
+1
-1
routines/templates/morning-briefing.md
+1
-1
routines/templates/morning-briefing.md
···
15
15
1. Call `sol call journal facets` to see the active facets if you need broader context.
16
16
2. Call `sol call calendar list $day_YYYYMMDD` to review today's events and participants.
17
17
3. Call `sol call todos list` to see pending action items across facets.
18
-
4. Call `sol call sol pulse` to capture current narrative, priorities, and needs-you items.
18
+
4. Call `sol call identity pulse` to capture current narrative, priorities, and needs-you items.
19
19
5. Call `sol call journal search "" -a followups -n 10` to find recent follow-up items.
20
20
6. For each person on today's calendar, call `sol call entities intelligence PERSON`.
21
21
7. If a facet needs more detail, call `sol call journal news FACET --day $day_YYYYMMDD`.
+1
-1
routines/templates/relationship-pulse.md
+1
-1
routines/templates/relationship-pulse.md
···
16
16
2. Use `sol call journal search "" --facet FACET -n 20` to identify frequently mentioned people or recent interactions in each relevant facet.
17
17
3. For each meaningful person, call `sol call entities intelligence PERSON`.
18
18
4. Use `sol call journal news FACET --day $day_YYYYMMDD` if a facet summary helps explain current context.
19
-
5. Use `sol call sol pulse` for broad priorities that may affect relationship maintenance.
19
+
5. Use `sol call identity pulse` for broad priorities that may affect relationship maintenance.
20
20
21
21
## Synthesize
22
22
+1
-1
routines/templates/weekly-review.md
+1
-1
routines/templates/weekly-review.md
···
16
16
2. Use `sol call journal search "" --day-from $day_minus_7_YYYYMMDD --day-to $day_YYYYMMDD -n 25` to find notable entries and themes.
17
17
3. Use `sol call todos list` to review outstanding work and infer what likely got completed or deferred.
18
18
4. Use `sol call calendar list YYYYMMDD` across the last 7 days to understand meeting load and major time commitments.
19
-
5. Use `sol call sol pulse` for the current state narrative.
19
+
5. Use `sol call identity pulse` for the current state narrative.
20
20
6. Use `sol call journal news FACET --day YYYYMMDD` for any facet that needs a richer summary.
21
21
22
22
## Synthesize
+4
-4
sol/identity.md
+4
-4
sol/identity.md
···
30
30
31
31
### How to write
32
32
33
-
Read current state: `sol call sol self` or `sol call sol agency`
33
+
Read current state: `sol call identity self` or `sol call identity agency`
34
34
35
-
Read partner profile: `sol call sol partner` (read-only — do not write in conversation)
35
+
Read partner profile: `sol call identity partner` (read-only — do not write in conversation)
36
36
37
37
Update a section of self.md (preferred — preserves other sections):
38
38
```
39
-
sol call sol self --update-section 'who I'\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie'
39
+
sol call identity self --update-section 'who I'\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie'
40
40
```
41
41
42
-
Full rewrite: `sol call sol self --write --value '...'` or `sol call sol agency --write --value '...'`
42
+
Full rewrite: `sol call identity self --write --value '...'` or `sol call identity agency --write --value '...'`
43
43
44
44
Use `sol call` commands for identity writes — never use `apply_patch` or direct file editing for sol/ files.
45
45
+2
-2
tests/test_sol_call.py
+2
-2
tests/test_sol_call.py
···
1
1
# SPDX-License-Identifier: AGPL-3.0-only
2
2
# Copyright (c) 2026 sol pbc
3
3
4
-
"""Tests for sol call sol — identity directory read/write commands."""
4
+
"""Tests for sol call identity — identity directory read/write commands."""
5
5
6
6
import json
7
7
···
306
306
307
307
308
308
class TestSolWriteDoesNotEscapeSolDir:
309
-
"""Verify that sol call sol only writes to sol/ directory files."""
309
+
"""Verify that sol call identity only writes to sol/ directory files."""
310
310
311
311
def test_self_write_stays_in_sol_dir(self, journal_with_sol):
312
312
"""Write to self.md goes to sol/self.md, not anywhere else."""
+3
-30
think/call.py
+3
-30
think/call.py
···
73
73
74
74
# Mount built-in CLIs (not auto-discovered since they live under think/)
75
75
from think.tools.call import app as journal_app
76
+
from think.tools.navigate import app as navigate_app
76
77
from think.tools.routines import app as routines_app
77
78
from think.tools.sol import app as sol_app
78
79
79
80
call_app.add_typer(journal_app, name="journal")
81
+
call_app.add_typer(navigate_app, name="navigate")
80
82
call_app.add_typer(routines_app, name="routines")
81
-
call_app.add_typer(sol_app, name="sol")
82
-
83
-
84
-
# General-purpose navigate command (migrated from apps/chat/call.py)
85
-
@call_app.command("navigate")
86
-
def navigate(
87
-
path: str = typer.Argument(None, help="URL path to navigate to."),
88
-
facet: str = typer.Option(None, "--facet", "-f", help="Facet to switch to."),
89
-
) -> None:
90
-
"""Navigate the browser to a path and/or switch facet."""
91
-
if not path and not facet:
92
-
typer.echo("Error: provide a path and/or --facet", err=True)
93
-
raise typer.Exit(1)
94
-
95
-
from think.callosum import callosum_send
96
-
97
-
fields: dict = {}
98
-
if path is not None:
99
-
fields["path"] = path
100
-
if facet is not None:
101
-
fields["facet"] = facet
102
-
103
-
callosum_send("navigate", "request", **fields)
104
-
105
-
parts = []
106
-
if path:
107
-
parts.append(path)
108
-
if facet:
109
-
parts.append(f"[{facet}]")
110
-
typer.echo(f"Navigate: {' '.join(parts)}")
83
+
call_app.add_typer(sol_app, name="identity")
111
84
112
85
113
86
def main() -> None: