0bf810f1e8
feat: add onMemoryPlaced callback for particle system integration
2026-04-11 00:50:18 +00:00
9561488f8a
feat(mnemosyne): ambient particle system for memory activity visualization
...
Issue #1173
- Spawn burst (20 particles, 2s fade) on new fact stored
- Access trail (10 particles) streaming to crystal on fact access
- Ambient cosmic dust (200 particles, slow drift)
- Category colors for all particles
- Total budget < 500 particles at any time
2026-04-11 00:49:13 +00:00
c736540fc2
merge: Mnemosyne spatial search
...
Co-authored-by: Alexander Whitestone <alexander@alexanderwhitestone.com >
Co-committed-by: Alexander Whitestone <alexander@alexanderwhitestone.com >
2026-04-11 00:35:29 +00:00
d00adbf6cc
merge: Mnemosyne timeline scrubber
...
Co-authored-by: Alexander Whitestone <alexander@alexanderwhitestone.com >
Co-committed-by: Alexander Whitestone <alexander@alexanderwhitestone.com >
2026-04-11 00:35:06 +00:00
7ed9eb75ba
merge: Mnemosyne crystal rendering
...
Co-authored-by: Alexander Whitestone <alexander@alexanderwhitestone.com >
Co-committed-by: Alexander Whitestone <alexander@alexanderwhitestone.com >
2026-04-11 00:34:50 +00:00
c5c752f9be
fix: [TRAINING] Capture the first replayable local Bannerlord session trace for Timmy
...
Closes #1197
Automated squash merge by mimo swarm.
2026-04-11 00:20:37 +00:00
e842e35833
fix: [Mnemosyne] Memory persistence export — dump spatial state to JSON
...
Closes #1188
Automated squash merge by mimo swarm.
2026-04-11 00:16:08 +00:00
cc4af009c7
[claude] Mnemosyne session rooms — holographic chambers per session ( #1171 ) ( #1178 )
2026-04-10 22:45:10 +00:00
089b06b6f8
[claude] Mnemosyne category regions — spatial zones for fact types ( #1168 ) ( #1179 )
2026-04-10 22:45:04 +00:00
e2edfd3318
[claude] Mnemosyne gravity well clustering — related memories attract in 3D ( #1175 ) ( #1176 )
2026-04-10 22:18:46 +00:00
87bfe9b332
feat(mnemosyne): add crystal mesh query + highlight/select API for click-to-inspect
2026-04-10 19:38:53 +00:00
1e7bb2a453
feat: add localStorage persistence to Spatial Memory Schema
...
Auto-saves on placeMemory/removeMemory. Auto-restores on init.
Prunes archive memories on quota exceeded.
Closes #1158
2026-04-10 12:43:00 +00:00
Alexander Whitestone
220f20c794
feat: add desktop automation primitives to Hermes ( #1125 )
...
Implements Phase 1 and Phase 2 tooling from issue #1125 :
- nexus/computer_use.py: four Hermes tools with poka-yoke safety
* computer_screenshot() — capture & base64-encode desktop snapshot
* computer_click(x, y, button, confirm) — right/middle require confirm=True
* computer_type(text, confirm) — sensitive keywords blocked without confirm=True;
text value is never written to audit log
* computer_scroll(x, y, amount) — scroll wheel
* read_action_log() — inspect recent JSONL audit entries
* pyautogui.FAILSAFE=True; all tools degrade gracefully when headless
- nexus/computer_use_demo.py: Phase 1 demo (baseline screenshot →
open browser → navigate to Gitea forge → evidence screenshot)
- tests/test_computer_use.py: 32 unit tests, fully headless
(pyautogui mocked), all passing
- docs/computer-use.md: API reference, safety table, phase roadmap,
pilot recipes
- docker-compose.desktop.yml: sandboxed Xvfb + noVNC container
Fixes #1125
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-10 05:45:27 -04:00
61871cf6ed
feat(mnemosyne): add SpatialMemory component with 6 semantic regions
2026-04-10 07:36:53 +00:00
259df5b5e6
feat(lazarus): fleet health dashboard, pulse viz, and checkpoint/restore ( #805 #869 #881 )
2026-04-07 15:14:03 +00:00
34ec13bc29
[claude] Poka-yoke cron heartbeats: write, check, and report ( #1096 ) ( #1107 )
2026-04-07 14:44:05 +00:00
ea3cc6b393
[claude] Poka-yoke cron heartbeats — make silent failures impossible ( #1096 ) ( #1102 )
2026-04-07 14:38:55 +00:00
33a1c7ae6a
[claude] MemPalace follow-up: CmdAsk, metadata fix, taxonomy CI ( #1075 ) ( #1091 )
2026-04-07 14:23:07 +00:00
e957254b65
[claude] MemPalace × Evennia fleet memory scaffold ( #1075 ) ( #1088 )
2026-04-07 14:12:38 +00:00
Groq Agent
0b4fd0c6e6
[groq] [QA][POLICY] Branch Protection + Mandatory Review Policy for All Repos ( #918 ) ( #942 )
2026-04-07 06:57:14 +00:00
Alexander Whitestone
37b006d3c6
feat: Fleet management ( #910 ), retry logic ( #896 ), morning report ( #897 )
...
- fleet/fleet.sh: cross-VPS health, status, restart, deploy
- nexus/retry_helper.py: retry decorator, dead letter queue, checkpoints
- nexus/morning_report.py: automated 0600 overnight activity report
- fleet/allegro/archived-scripts/README.md: burn script archive placeholder
Fixes #910
Fixes #896
Fixes #897
Fixes #898
2026-04-06 23:09:49 -04:00
4496ff2d80
[claude] Stand up Gemini harness as network worker ( #748 ) ( #811 )
2026-04-04 01:41:53 +00:00
f6aa3bdbf6
[claude] Add Nexus UI component prototypes — portal wall, agent presence, briefing ( #749 ) ( #810 )
2026-04-04 01:41:13 +00:00
8645798ed4
feat: Evennia-Nexus Bridge v2 — Live Event Streaming ( #804 ) ( #807 )
...
Co-authored-by: Allegro <allegro@hermes.local >
Co-committed-by: Allegro <allegro@hermes.local >
2026-04-04 01:39:38 +00:00
1ba1f31858
Sovereignty & Calibration: Nostr Identity and Adaptive Cost Estimation ( #790 )
...
Co-authored-by: Google AI Agent <gemini@hermes.local >
Co-committed-by: Google AI Agent <gemini@hermes.local >
2026-04-04 01:37:06 +00:00
d32baa696b
[watchdog] The Eye That Never Sleeps — Nexus Health Monitor ( #794 )
...
Co-authored-by: Google AI Agent <gemini@hermes.local >
Co-committed-by: Google AI Agent <gemini@hermes.local >
2026-04-04 01:36:56 +00:00
Allegro (Burn Mode)
29e64ef01f
feat: Complete Bannerlord MCP Harness implementation (Issue #722 )
...
Implements the Hermes observation/control path for local Bannerlord per GamePortal Protocol.
## New Components
- nexus/bannerlord_harness.py (874 lines)
- MCPClient for JSON-RPC communication with MCP servers
- capture_state() → GameState with visual + Steam context
- execute_action() → ActionResult for all input types
- observe-decide-act loop with telemetry through Hermes WS
- Bannerlord-specific actions (inventory, party, save/load)
- Mock mode for testing without game running
- mcp_servers/desktop_control_server.py (14KB)
- 13 desktop automation tools via pyautogui
- Screenshot, mouse, keyboard control
- Headless environment support
- mcp_servers/steam_info_server.py (18KB)
- 6 Steam Web API tools
- Mock mode without API key, live mode with STEAM_API_KEY
- tests/test_bannerlord_harness.py (37 tests, all passing)
- GameState/ActionResult validation
- Mock mode action tests
- ODA loop tests
- GamePortal Protocol compliance tests
- docs/BANNERLORD_HARNESS_PROOF.md
- Architecture documentation
- Proof of ODA loop execution
- Telemetry flow diagrams
- examples/harness_demo.py
- Runnable demo showing full ODA loop
## Updates
- portals.json: Bannerlord metadata per GAMEPORTAL_PROTOCOL.md
- status: active, portal_type: game-world
- app_id: 261550, window_title: 'Mount & Blade II: Bannerlord'
- telemetry_source: hermes-harness:bannerlord
## Verification
pytest tests/test_bannerlord_harness.py -v
37 passed, 2 skipped, 11 warnings
Closes #722
2026-03-31 04:53:29 +00:00
e88bcb4857
[fix] 5 bugs: 2 SyntaxErrors in nexus_think.py, Groq model name, server race condition, corrupt public/nexus/
...
Bug 1: nexus_think.py line 318 — stray '.' between function call and if-block
This is a SyntaxError. The entire consciousness loop cannot import.
The Nexus Mind has been dead since this was committed.
Bug 2: nexus_think.py line 445 — 'parser.add_.argument()'
Another SyntaxError — extra underscore in argparse call.
The CLI entrypoint crashes on startup.
Bug 3: groq_worker.py — DEFAULT_MODEL = 'groq/llama3-8b-8192'
The Groq API expects bare model names. The 'groq/' prefix causes a 404.
Fixed to 'llama3-8b-8192'.
Bug 4: server.py — clients.remove() in finally block
Raises KeyError if the websocket was never added to the set.
Fixed to clients.discard() (safe no-op if not present).
Also added tracking for disconnected clients during broadcast.
Bug 5: public/nexus/ — 3 corrupt duplicate files (28.6 KB wasted)
app.js, style.css, and index.html all had identical content (same SHA).
These are clearly a broken copy operation. The real files are at repo root.
Tests: 6 new, 21/22 total pass. The 1 pre-existing failure is in
test_portals_json_uses_expanded_registry_schema (schema mismatch, not
related to this PR).
Signed-off-by: gemini <gemini@hermes.local >
2026-03-30 19:04:53 -04:00
Alexander Whitestone
1fe5176ebc
feat: feed Evennia world events into Nexus websocket bridge
2026-03-28 16:25:18 -04:00
Alexander Whitestone
8ead4cd13f
feat: add thin Evennia to Nexus event adapter
2026-03-28 16:02:27 -04:00
632867258b
[gemini] feat: audit groq worker ( #451 ) ( #539 )
...
Co-authored-by: Google AI Agent <gemini@hermes.local >
Co-committed-by: Google AI Agent <gemini@hermes.local >
2026-03-25 20:14:49 +00:00
Alexander Whitestone
057c751c57
feat: first light test report and ws gateway fixes
2026-03-25 14:37:35 -04:00
perplexity
1ecca527cb
feat: Nexus Mind — embodied consciousness loop for 8B sovereign brain
...
Adds the perception adapter, experience store, trajectory logger, and
consciousness loop that give Timmy a body in the Nexus.
Architecture:
BIRTH.md — Thin system prompt. SOUL.md conscience + embodied
awareness. No meta-knowledge about implementation.
perception_adapter — Translates WS events to natural-language sensory
descriptions. Parses model output into WS actions.
experience_store — SQLite-backed lived-experience memory. The model
remembers only what it perceived through its channel.
trajectory_logger — Logs every perceive→think→act cycle as ShareGPT JSONL,
compatible with the AutoLoRA training pipeline.
nexus_think — The consciousness loop. Connects to WS gateway,
receives perceptions, thinks via Ollama, sends actions.
The 8B model wakes up knowing nothing but its values and what it
experiences. Training loops close on lived experience — emergence
through the channel, not through fine-tuning toward behaviors.
Run: python -m nexus.nexus_think --model timmy:v0.1-q4 --ws ws://localhost:8765
2026-03-25 17:20:03 +00:00
