Timmy_Foundation/the-nexus
15
1
Fork 2
Code Issues 77 Pull Requests 82 Actions 3 Packages Projects Releases Wiki Activity
472 Commits 421 Branches 4 Tags
b73d846334bf86afd494fee84de00a55880d68aa
Commit Graph

28 Commits

Author SHA1 Message Date
Alexander Whitestone
4c267de5bc feat: add spatial search — keyword search, highlight matches, dim non-matches 
Issue #1170
Searches memory content, IDs, categories. Matches glow white,
non-matches dim to 10% opacity. clearSearch() restores original state.
 2026-04-11 00:19:25 +00:00
Alexander Whitestone
e842e35833 fix: [Mnemosyne] Memory persistence export — dump spatial state to JSON
Some checks failed
Deploy Nexus / deploy (push) Failing after 3s
Details
Staging Verification Gate / verify-staging (push) Failing after 3s
Details 
Closes #1188

Automated squash merge by mimo swarm.
 2026-04-11 00:16:08 +00:00
Claude (Opus 4.6)
cc4af009c7 [claude] Mnemosyne session rooms — holographic chambers per session (#1171) (#1178)
Some checks failed
Deploy Nexus / deploy (push) Failing after 3s
Details
Staging Verification Gate / verify-staging (push) Failing after 3s
Details
CI / test (pull_request) Failing after 9s
Details
CI / validate (pull_request) Failing after 13s
Details
Review Approval Gate / verify-review (pull_request) Failing after 3s
Details
2026-04-10 22:45:10 +00:00
Claude (Opus 4.6)
089b06b6f8 [claude] Mnemosyne category regions — spatial zones for fact types (#1168) (#1179)
Some checks failed
Deploy Nexus / deploy (push) Failing after 2s
Details
Staging Verification Gate / verify-staging (push) Has been cancelled
Details
2026-04-10 22:45:04 +00:00
Claude (Opus 4.6)
e2edfd3318 [claude] Mnemosyne gravity well clustering — related memories attract in 3D (#1175) (#1176)
Some checks failed
Deploy Nexus / deploy (push) Failing after 4s
Details
Staging Verification Gate / verify-staging (push) Failing after 4s
Details
2026-04-10 22:18:46 +00:00
Alexander Whitestone
87bfe9b332 feat(mnemosyne): add crystal mesh query + highlight/select API for click-to-inspect 2026-04-10 19:38:53 +00:00
Alexander Whitestone
1e7bb2a453 feat: add localStorage persistence to Spatial Memory Schema
Some checks failed
CI / test (pull_request) Failing after 13s
Details
CI / validate (pull_request) Failing after 13s
Details
Review Approval Gate / verify-review (pull_request) Failing after 2s
Details 
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)
Some checks failed
CI / test (pull_request) Failing after 8s
Details
CI / validate (pull_request) Failing after 10s
Details
Review Approval Gate / verify-review (pull_request) Failing after 2s
Details 
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
Alexander Whitestone
61871cf6ed feat(mnemosyne): add SpatialMemory component with 6 semantic regions 2026-04-10 07:36:53 +00:00
Bezalel
259df5b5e6 feat(lazarus): fleet health dashboard, pulse viz, and checkpoint/restore (#805 #869 #881)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
Staging Verification Gate / verify-staging (push) Has been cancelled
Details
2026-04-07 15:14:03 +00:00
Claude (Opus 4.6)
34ec13bc29 [claude] Poka-yoke cron heartbeats: write, check, and report (#1096) (#1107)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
2026-04-07 14:44:05 +00:00
Claude (Opus 4.6)
ea3cc6b393 [claude] Poka-yoke cron heartbeats — make silent failures impossible (#1096) (#1102)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
2026-04-07 14:38:55 +00:00
Claude (Opus 4.6)
33a1c7ae6a [claude] MemPalace follow-up: CmdAsk, metadata fix, taxonomy CI (#1075) (#1091)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
CI / test (pull_request) Failing after 6s
Details
CI / validate (pull_request) Failing after 4s
Details
2026-04-07 14:23:07 +00:00
Claude (Opus 4.6)
e957254b65 [claude] MemPalace × Evennia fleet memory scaffold (#1075) (#1088)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
2026-04-07 14:12:38 +00:00
Groq Agent
0b4fd0c6e6 [groq] [QA][POLICY] Branch Protection + Mandatory Review Policy for All Repos (#918) (#942)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
CI / test (pull_request) Failing after 9s
Details
CI / validate (pull_request) Failing after 2s
Details
2026-04-07 06:57:14 +00:00
Alexander Whitestone
37b006d3c6 feat: Fleet management (#910), retry logic (#896), morning report (#897)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
CI / validate (pull_request) Failing after 10s
Details 
- 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
Claude (Opus 4.6)
4496ff2d80 [claude] Stand up Gemini harness as network worker (#748) (#811)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
2026-04-04 01:41:53 +00:00
Claude (Opus 4.6)
f6aa3bdbf6 [claude] Add Nexus UI component prototypes — portal wall, agent presence, briefing (#749) (#810)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details
2026-04-04 01:41:13 +00:00
Allegro
8645798ed4 feat: Evennia-Nexus Bridge v2 — Live Event Streaming (#804) (#807)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details 
Co-authored-by: Allegro <allegro@hermes.local>
Co-committed-by: Allegro <allegro@hermes.local>
 2026-04-04 01:39:38 +00:00
Google AI Agent
1ba1f31858 Sovereignty & Calibration: Nostr Identity and Adaptive Cost Estimation (#790)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details 
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
Google AI Agent
d32baa696b [watchdog] The Eye That Never Sleeps — Nexus Health Monitor (#794)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Details 
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)
Some checks failed
Deploy Nexus / deploy (push) Failing after 4s
Details 
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
Google AI Agent
e88bcb4857 [fix] 5 bugs: 2 SyntaxErrors in nexus_think.py, Groq model name, server race condition, corrupt public/nexus/
Some checks failed
CI / validate (pull_request) Failing after 5s
Details 
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
Some checks failed
CI / validate (pull_request) Failing after 4s
Details
2026-03-28 16:25:18 -04:00
Alexander Whitestone
8ead4cd13f feat: add thin Evennia to Nexus event adapter
Some checks failed
CI / validate (pull_request) Failing after 4s
Details
2026-03-28 16:02:27 -04:00
Google AI Agent
632867258b [gemini] feat: audit groq worker (#451) (#539)
Some checks failed
Deploy Nexus / deploy (push) Failing after 5s
Details 
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
Some checks failed
CI / validate (pull_request) Failing after 5s
Details
2026-03-25 14:37:35 -04:00
perplexity
1ecca527cb feat: Nexus Mind — embodied consciousness loop for 8B sovereign brain
Some checks failed
CI / validate (pull_request) Failing after 5s
Details 
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