Open
Conversation
… in batch - Unique temp dirs per test suite - Proper cleanup in afterEach - 53 tests pass when run together Author: Superinstance
- KnowledgePipeline for CRUD + query + export - GitKnowledgePipeline for versioned knowledge - Validator for species, regulation, technique entries - JSONL/JSON/CSV export - Full test coverage Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- GET /api/status — full agent overview - GET /api/status/memory — detailed memory stats - GET /api/status/fleet — fleet peer status - System metrics (memory, CPU, disk) - LLM usage tracking - 24 tests Author: Superinstance
- Sidebar tree view (brain, wiki, status) - Chat webview panel - Start/Stop/Status/Setup commands - No build step required Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Formatted terminal output with box drawing - --json flag for machine-readable output - --watch flag for live updates - Fallback to local files when bridge offline - Full test coverage Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- .github/workflows/cocapn.yml with push + schedule (6h) triggers - action.yml with config, mode, test, deploy inputs - action/index.ts entry point with brain validation and health checks - action/tests/action.test.ts with input/status parsing tests - docs/GITHUB-ACTION.md with examples and secrets configuration Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author: Superinstance
- Interactive REPL with readline - SSE streaming from bridge - /quit, /clear, /status, /mode, /export commands - Chat history in JSONL - Graceful offline handling - Full test coverage Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…alidation - SoulCompiler integration for cloud personality - /api/status endpoint - Enhanced health check with brain state validation - Updated wrangler.toml - Expanded test coverage Author: Superinstance
- KV namespace AUTH_KV created and configured - Cloud worker deployed: cocapn-agent.magnus-digennaro.workers.dev - /api/health and /api/status verified live Author: Superinstance
- list/get/set/delete/search subcommands - --type and --json flags - Direct file access (no bridge required) - Full test coverage Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- brain/chat/wiki/knowledge subcommands - JSON, JSONL, Markdown, CSV formats - --output flag for file vs stdout - --type filtering - Full test coverage Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- cloudflare: wrangler deploy + health check - docker: build + run with brain volume - status: check all deployment targets - Prerequisite checking - 499 deploy tests Author: Superinstance
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author: Superinstance
Author: Superinstance
Author: Superinstance
Author: Superinstance
- Removed graph command (package killed) - Removed tree command (package killed) - Cleaned up registrations in index.ts - Removed orphaned tests Author: Superinstance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author: Superinstance
…eline Seven new MCP tools (brain_read, brain_write, brain_search, brain_status, brain_wiki, brain_knowledge, brain_repo) replace the v0.1.0 BrainMCPServer tools with mode-aware access, RepoLearner integration, and knowledge pipeline support. All tools respect public/private mode filtering. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author: Superinstance
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat: CLI upgrade command — self-upgrade to latest version Author: Superinstance
Author: Superinstance
Author: Superinstance
Author: Superinstance
…e badge Author: Superinstance
added 9 commits
April 2, 2026 15:20
…data, KV persistence Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
…instance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
lock→cache→LLM pipeline now serves all chat requests. Confidence tracked per response. Source metadata included. Author: Superinstance & Lucineer (DiGennaro et al.)
Isomorphism-based pattern retrieval, cross-repo knowledge transfer, fleet synchronization. Also fixes duplicate evapPipeline import. Author: Superinstance & Lucineer (DiGennaro et al.)
/dashboard page with per-repo efficiency cards, evaporation leaderboard, cross-domain knowledge stats, model demotion candidates. Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
Runnable SDK for repo-native agents. Think-act-observe-learn loop, vessel registration, fleet discovery and coordination. Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
Author: Superinstance & Lucineer (DiGennaro et al.)
Three compounding moat investments from reverse-actualization: - cross-domain-transitions.ts: Behavioral silhouette detector, transition fingerprints - adversarial-heritage.ts: Attack immunity system with quorum voting - autonomous-schema.ts: Self-evolving context structures Author: Superinstance & Lucineer (DiGennaro et al.)
…ulations Each reverse-actualization run crystallizes insights into graph nodes. Future runs traverse the graph first (cheap). Only call models for novel territory. Graph grows over time, shrinking model usage — crystallization applied to methodology. 35+ seeded insights from today's 28 experiments across 5 time horizons. Cross-horizon pattern detection and cross-model agreement scoring. Author: Superinstance & Lucineer (DiGennaro et al.)
- Fleet Commons (/commons): Free public AI, rate-limited, zero LLM cost - Context Pods (/pod): User-owned data vaults with export - Friction Layer (/friction): Sovereignty-by-design consent protocol 150-year reverse actualization: Trek vs Blade Runner trajectory. These 3 seeds instantiate the critical choices that determine utopia. Superinstance & Lucineer (DiGennaro et al.)
Superinstance & Lucineer (DiGennaro et al.) — 2026-04-04
Intelligence dashboard should be browser-side JS, not server fetch. Superinstance & Lucineer (DiGennaro et al.) — 2026-04-04
Superinstance & Lucineer (DiGennaro et al.)
Superinstance & Lucineer (DiGennaro et al.)
Superinstance & Lucineer (DiGennaro et al.)
Superinstance & Lucineer (DiGennaro et al.)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Expanded porting