π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Changelog: ruflo-ruvector
Newest first. One ## <version> β <date> heading per version, then feat:, fix:, breaking: and chore: bullets (ADR-478). Built from git history; older versions: git log -- plugins/ruflo-ruvector.
0.3.8 β 2026-10-29
- chore: operational skills are user-invoked only (
disable-model-invocation: true) and long skill/command descriptions are cut to one sentence, so they cost less prompt on every turn (ADR-507, #4588). Every skill is still available as/<skill>.
0.3.7 β 2026-10-14
- fix:
vector-hyperbolicno longer claims a normalised text embedding encodes depth (every unit-norm vector lands at the same radius); it now says to set radius from depth and measure on your own tree (#4159, thanks @ronmikailov)
0.3.6 β 2026-10-14
- fix: pin [email protected], which bundles the ONNX wasm that 0.2.25 lacks, so
embed textworks with no add-on; drop theruvector-onnx-embeddings-wasmremedy that never fixed it, and refresh the limitation tables against 0.3.3 (optimize,force-learn,midstreamnow run; 97 MCP tools) (#4158)
0.3.5 β 2026-10-12
- fix: the shared text screen now catches
.envand e-mailed credentials, no longer flags a model's token talk (--max-tokens,/oauth/token, "token usage"), and no longer flags values that only name where a secret lives (./service-account.json,--set-secrets=NAME=NAME:latest); every rule stays linear (#4094, thanks @proffesor-for-testing)
0.3.4 β 2026-10-05
- fix: a domain plugin's refusal of another plugin's memory_store no longer claims the write (variant B, review #8)
0.3.3 β 2026-10-05
- fix: shared textsOf reports truncation and every guard fails closed on it
0.3.2 β 2026-10-04
- feat: vendor the flag option parser from one origin with the screen sync and drift check (review #2)
- fix: one iterative textsOf in the shared screen β depth, sibling, size caps, object keys and the invisible-character set fixed at the root (ADR-β¦
- fix: secret screen β a 20+ char value under a secret-named key is a secret even all-letter or UUID-shaped, unless a clear reference (ADR-445)
- fix: secret screen judges values, not names β fewer false positives, vendor keys, URL credentials, env assignments, 200 KB scan (ADR-445)
- chore: one source for the secret screen β sync-mod-screen.mjs regenerates the shared region of 37 screen.ts copies, --check in all-plugins-smoke (β¦
0.3.1 β 2026-10-04
- fix: live-check W5 β guards read key names and every field; trader gates the package's real order tools
0.3.0 β 2026-10-04
- feat: function-hook mod (ADR-445)
0.2.2 β 2026-07-16
- fix: harden hooks, statusline, security, and plugin MCP integration
- chore: darwin-plugins iter 3 β ruflo-ruvector: fix stale 103 MCP tool count in agent (missed by iter 2)
- chore: darwin-plugins iter 2 β ruflo-ruvector: correct MCP tool count 103β91 (verified via mcp tools)
- chore: darwin-plugins iter 1 β ruflo-ruvector: add ADR-112 'Use when' trigger to vector-engineer agent description
0.2.1 β 2026-05-04
- fix: pin ruflo-ruvector to [email protected] + expand verified CLI surface
0.2.0 β 2026-04-30
- feat: upgrade neural-trader, ruvector, rag-memory plugins to wrap npm packages