Bridge the gap between "stores knowledge" and "learns from knowledge":
- Background training loop (tokio::spawn, 5 min interval) runs SONA
force_learn + domain evolve_population when new data arrives
- POST /v1/train endpoint for on-demand training cycles
- `ruvector brain train` CLI command with --json support
- `brain_train` MCP tool for agent-triggered training
- Vote dedup: 24h TTL on ip_votes entries, author exemption from IP check
- ADR-082 updated, ADR-083 created
Results: Pareto frontier grew 0→24 after 3 cycles. SONA activates
after 100+ trajectory threshold (natural search/share usage).
Publish ruvector@0.2.11.
* feat: proxy-aware fetch + brain API improvements — publish v0.2.7
Add proxyFetch() wrapper to cli.js and mcp-server.js that detects
HTTPS_PROXY/HTTP_PROXY/ALL_PROXY env vars, uses undici ProxyAgent
(Node 18+) or falls back to curl. Handles NO_PROXY patterns.
Replaced all 17 fetch() call sites with timeouts (15-30s).
Brain server API:
- Search returns similarity scores via ScoredBrainMemory
- List supports pagination (offset/limit), sorting (updated_at/quality/votes), tag filtering
- Transfer response includes warnings, source/target memory counts
- New POST /v1/verify endpoint with 4 verification methods
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat: brain server bug fixes, GET /v1/pages, 9 MCP page/node tools — v0.2.10
Fix proxyFetch curl fallback to capture real HTTP status instead of
hardcoding 200, add 204 guards to brainFetch/fetchBrainEndpoint/MCP
handler, fix brain_list schema (missing offset/sort/tags), fix
brain_sync direction passthrough, add --json to share/vote/delete/sync.
Add GET /v1/pages route with pagination, status filter, sort.
Add 9 MCP tools: brain_page_list/get/create/update/delete,
brain_node_list/get/publish/revoke (previously SSE-only).
Polish: delete --json returns {deleted:true,id} not {}, page get
unwraps .memory wrapper for formatted display.
112 MCP tools, 69/69 tests pass. Published v0.2.10 to npm.
Co-Authored-By: claude-flow <ruv@ruv.net>
- Introduced QUICKSTART.md for RuVector, detailing setup, usage, and architecture.
- Added ruvector-knowledge.rvf.json for comprehensive project metadata, including architecture overview, crate taxonomy, and critical decisions.
- GETTING_STARTED.md: rewrite to cover both ruvector-core (VectorDB) and
rvf-runtime (RvfStore) APIs, add package registry table, fix SearchQuery
fields (ef_search not include_vectors), results use .score not .distance
- INSTALLATION.md: update crate version 0.1.0 -> 2.0, fix npm scoped
package names (@ruvector/*), remove non-existent Docker image, update
Rust version requirement to 1.80+, fix CLI docs to match actual subcommands
- BASIC_TUTORIAL.md: fix SearchQuery.include_vectors -> ef_search, fix
result.distance -> result.score, fix HnswConfig/QuantizationConfig field
access patterns (options.hnsw -> options.hnsw_config, wrap in Some())
- ADVANCED_FEATURES.md: same field name fixes, fix QuantizationConfig
wrapping in Some(), remove references to non-existent mmap_vectors field
- docs/README.md: update version to 2.0.4/0.1.100, update date
Co-Authored-By: claude-flow <ruv@ruv.net>
Research three GitHub projects sharing the OpenFang name:
- RightNow-AI/openfang: Rust-based Agent OS (most significant)
- anmaped/openfang: Camera firmware for Ingenic T20 (dormant)
- danshorstein/OpenFang: Python AI assistant fork
https://claude.ai/code/session_015KgxqLUhevxop1jhiZY2Y4
Implement trait-based IntelligenceProvider extension point for external
quality signals. Addresses PR #190 proposal (renumbered from ADR-029 to
avoid collision with existing ADR-029-rvf-canonical-format).
- IntelligenceProvider trait with load_signals() and quality_weights()
- FileSignalProvider built-in for JSON file-based signal exchange
- IntelligenceLoader for multi-provider registration and aggregation
- QualitySignal, QualityFactors, ProviderQualityWeights types
- calibration_bias() on TaskComplexityAnalyzer for router feedback
- 12 unit tests (all passing)
Co-Authored-By: claude-flow <ruv@ruv.net>
- solver_benchmark.rs: Store benchmark results in RVF for analysis
- Updated solver_witness.rs with refinements
- Updated examples/rvf/Cargo.toml with 3 new [[example]] entries
- Updated examples/rvf/src/lib.rs with new example documentation
- Refined AGI sublinear optimization review
https://claude.ai/code/session_01TiqLbr2DaNAntQHaVeLfiR
- All 10 ADR-STS documents updated from Proposed to Accepted
- Added implementation status sections reflecting delivered solver crate
- Updated SOTA research analysis to v3.0 with implementation realization
- Updated optimization guide to v2.0 with realized optimizations
- Updated executive summary, performance, algorithm, and testing docs
- Added solver_witness.rs RVF example
https://claude.ai/code/session_01TiqLbr2DaNAntQHaVeLfiR
Add 15 architecture and design documents covering the sublinear-time solver
integration into RuVector's 79-crate ecosystem:
ADR Documents (12):
- ADR-STS-001: Core integration architecture with trait hierarchy and event sourcing
- ADR-STS-002: Algorithm selection and sublinear routing with SONA adaptive learning
- ADR-STS-003: Memory management strategy with arena allocator and HNSW integration
- ADR-STS-004: WASM and cross-platform compilation with SIMD per architecture
- ADR-STS-005: Security model with STRIDE/DREAD analysis and witness chain audit
- ADR-STS-006: Benchmark framework with 6 Criterion.rs suites and CI regression
- ADR-STS-007: Feature flag and progressive rollout strategy
- ADR-STS-008: Error handling and fault tolerance with fallback chains
- ADR-STS-009: Concurrency model with Rayon+SIMD two-level parallelism
- ADR-STS-010: API surface design for Rust/WASM/NAPI/REST/MCP
- SOTA research analysis surveying 20+ papers and competitive landscape
- Optimization guide with SIMD/memory/algorithm/platform strategies
DDD Documents (3):
- Strategic design: 6 bounded contexts, context map, ubiquitous language
- Tactical design: aggregates, entities, value objects, domain services
- Integration patterns: ACLs, shared kernel, published language, event-driven
https://claude.ai/code/session_01TiqLbr2DaNAntQHaVeLfiR
Maps 7 concrete integration points between rvDNA genomics suite and
sublinear-time-solver: protein contact graph PageRank (500x speedup),
sparse attention solve in RVDNA format, joint variant calling with LD
(+15-30% sensitivity), sublinear Horvath clock regression, HNSW graph
optimization for pangenome k-mer search, network-based cancer detection
(3-5x sensitivity), and DNA storage/computation convergence.
Includes phased integration roadmap and scale impact analysis.
https://claude.ai/code/session_01WY4MpWoe2LMzkYUHLxhPHX
10 breakthrough vectors mapping concrete code paths to 50-year-ahead SOTA:
sub-constant time via predictive precomputation, self-discovering algorithms,
photonic-native vector ops, self-booting mathematical universes, neuromorphic
sublinear computing, hyperbolic sublinear geometry, cryptographic proof of
computation, temporal-causal vector spaces, infinite-scale sublinear consensus,
and the convergence of database + intelligence into a single substrate.
5-horizon roadmap from integration (2026) through convergence (2076).
https://claude.ai/code/session_01WY4MpWoe2LMzkYUHLxhPHX
Complete mathematical analysis of all 7 sublinear algorithms mapped to
ruvector's 9 subsystems. Top findings: Forward Push for hybrid graph
search (O(1/eps) vs O(k*d^L)), Conjugate Gradient for PDE attention
(quadratic to near-linear), Neumann Series for spectral filtering.
This completes the 15-agent analysis swarm - all documents present:
00-executive-summary, 01-14 covering crates, npm, rvf, examples,
architecture, wasm, mcp, performance, security, algorithms, typescript,
testing, dependencies, and roadmap.
https://claude.ai/code/session_01WY4MpWoe2LMzkYUHLxhPHX
Integration test design, property-based testing for solver correctness,
WASM test strategies, performance regression testing, and CI/CD pipeline
integration recommendations.
https://claude.ai/code/session_01WY4MpWoe2LMzkYUHLxhPHX
Full dependency tree comparison between ruvector (79 workspace members)
and sublinear-time-solver (9 crates), version conflicts, feature flag
compatibility, and bundle size impact.
https://claude.ai/code/session_01WY4MpWoe2LMzkYUHLxhPHX
