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-knowledge-graph
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.
0.3.6 β 2026-10-14
- fix: kg-traverse reads edges with
agentdb_graph-query(k-hop) andagentdb_graph-pathfinder, not the write-onlyagentdb_causal-edge; it no longer callsagentdb_context-synthesize(entity records are not validated task episodes, so it always answeredno-eligible-episodes) and says what to do when encryption at rest (RFE1) makes the graph unreadable; the graph-navigator agent lists the same read tools (#4135, #4161, thanks @ronmikailov)
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 2026-10-11
- Fix: relation weights in the
graph-navigatoragent disagreed withkg-extract(imports 1.0 vs 0.9, implements 0.9 vs 0.7, references 0.5 vs 0.3) and omittedtype-depends-on; aligned to the skill. Removed invalidneural train --pattern-type knowledge-graph(the flag is--patternwith a fixed set of values) and--train-neural.
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: jujutsu, knowledge-graph, loop-workers, market-data, metaharness as mods (ADR-445)
0.2.1 β 2026-07-16
- fix: harden hooks, statusline, security, and plugin MCP integration
- fix: reconcile stale smoke contract assertions across 23 plugins
- fix: #2049 β separate
import typefrom value imports + drop disabled semantic-route + CI guard - fix: correct embeddings_embed β embeddings_generate + adopt plugin contract (ADR-0001)
- chore: darwin-plugins iter 3 β ruflo-knowledge-graph: flag semantic-route as disabled in agent tool list (matches kg.md + ADR-0001)
- chore: darwin-plugins iter 2 β ruflo-knowledge-graph: fix README namespace claim (kg-graph β knowledge-graph) to match actual code
- chore: darwin-plugins iter 1 β ruflo-knowledge-graph: kg search uses pattern-search (semanticRouter disabled per #2049)
- chore: bulk-update plugin contract ADR statuses (sweep)
0.2.0 β 2026-05-03
- feat: ADR-098 Part 1 (slice 4/4) β G7 controllers in agentdb + knowledge-graph
0.1.0 β 2026-04-29
- feat: add 10 new ruflo plugins, optimize all 32, add READMEs and user guide