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-intelligence
Newest first. One ## <version> β <date> heading per version, then feat:, fix:, breaking: and chore: bullets (ADR-478). Built from git history; this is the whole history.
0.4.5 β 2026-10-14
- fix: neural-train step 6 passes
data(neural_train only learns from it and now answerssuccess: false, status: "empty"without it), and step 8 saysneural_patterns/neural_predictdo not see what trajectories, SONA and the ReasoningBank learned (a separate store; check it withhooks_intelligence_pattern-search/hooks_intelligence_stats) and thatneural_predictapplies a similarity floor (#4156); intelligence-transfer uses the top-leveltransfer-storecommand (the nestedhooks transfer store <sub>only printed help) and warns that the built-in genesis registry is an offline placeholder, not signed or popular data (#4157; thanks @ronmikailov)
0.4.4 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)
0.4.3 β 2026-10-11
- Fix: skills, commands and README called tools and CLI flags that do not exist or have different parameters (checked against
@claude-flow/cli3.56.5--helpand the MCP tool schemas):neural_trainneedsmodelType(there is nopatternType/--pattern-type; the CLI flag is--pattern),neural patterns --listis--action list,hooks pretrain/build-agents/explainflags,hooks_model-outcometakes{ task, model, outcome },hooks_intelligence_trajectory-endtakes a booleansuccess,ruvllm_microlora_adapthas no consolidate option (EWC++ runs inhooks_intelligence_learn), andmcp tool callismcp exec -t TOOL -p JSON. - Fix:
intelligence-transferclaimedhooks_transferpublishes to and loads from IPFS by CID. It only copies patterns from another local project ({ sourcePath, filter, minConfidence }); marketplace browse/download/publish ishooks transfer store ...and needsPINATA_API_KEY+PINATA_API_SECRET. The skill is rewritten accordingly, with a PII scan and explicit confirmation before any publish. - Fix:
hooks_intelligenceis a status call (it echoesmode); the README no longer says it switches architecture. Removed the invalidpost-task --train-neuralflag from examples.
0.4.2 β 2026-10-05
- fix: shared textsOf reports truncation and every guard fails closed on it
0.4.1 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¦
0.4.0 β 2026-10-04
- feat: goals, graph-intelligence, intelligence, iot-cognitum as mods
0.3.1 β 2026-07-16
- fix: harden hooks, statusline, security, and plugin MCP integration
- chore: darwin-plugins iter 3 β ruflo-intelligence: align plugin.json tool-count breakdown with README inventory
- chore: darwin-plugins iter 1 β ruflo-intelligence: correct Tier 1 to deterministic codemod (ADR-143)
0.3.0 β 2026-05-04
- feat: v0.3.0 β surface completeness, 4-step pipeline, IPFS transfer, namespace coordination
- feat: ADR-098 Part 4 β standardize neural-learning hook
- feat: add 10 new ruflo plugins, optimize all 32, add READMEs and user guide
0.1.0 β 2026-04-27
- feat: add 19 Claude Code native plugins with 64 skills, 25 commands, 21 agents