Issues

ruFlo Summit — Budapest (June 2–3, 2026)
#1967 · ruvnet opened on May 13, 2026
6
📖 How to contribute — read this first (pinned)
#2035 · ruvnet opened on May 17, 2026

[Dream Cycle 2026-06-12] intelligence: Agents-K1 KG gap — flat HNSW ReasoningBank cannot multi-hop; −80% TTFT from interleaved RL + capabilities,memory scan

capabilities

dream-cycle

#2362

· ruvnet opened

on Jun 12, 2026

Daemon self-terminating TTL + global status, honest HNSW/init footguns (carry-forward from pacphi/ruflo-machine-ref)

#2360

· shaal opened

on Jun 12, 2026

feat(router): Claude Fable 5 frontier routing tier — design, full change-point map, and a temperature 400 that blocks the entire Opus 4.7/4.8/Fable family today

#2357

· HF-teamdev opened

on Jun 11, 2026

agent_execute requires its own LLM provider key — should delegate inference to the MCP host (e.g. Codex) via MCP sampling

#2356

· Tovli opened

on Jun 11, 2026

[Dream Cycle 2026-06-11] security: runtime governance gap — Microsoft AGT forecloses 7 ASI risks at <0.1ms; Ruflo has no policy engine + intelligence,swarm scan

#2353

· ruvnet opened

on Jun 11, 2026

Superseded community PRs are orphaned when their fix merges via a different (batch) PR

#2349

· shaal opened

on Jun 10, 2026

[Dream Cycle 2026-06-10] performance: DeLM shared-context +10.5pp SWE-bench gap (−50% cost) + security,hive-mind scan

#2343

· ruvnet opened

on Jun 10, 2026

feat(agents): integrate Claude Code nested-subagent (depth=5) capability — ADR-147

enhancement

#2335

· ruvnet opened

on Jun 9, 2026

model router: exploring Option B — wire `@ruvector/tiny-dancer` FastGRNN through the now-documented embedding seam (follow-up to #2329)

#2334

· rcraw opened

on Jun 9, 2026

[Dream Cycle 2026-06-09] swarm: RL orchestration 5-decision gap (no stopping-RL in any framework) + ruview-integration,ruvector-integration scan

#2332

· ruvnet opened

on Jun 9, 2026

[dream-cycle] meta: ADR-147 collision across 6 open PRs + 0 merges in 14 nights

dream-cycle

#2324

· ruvnet opened

on Jun 8, 2026

[Dream Cycle 2026-06-08] memory: multi-signal retrieval gap vs Mem0 SOTA (94.4% LongMemEval) + plugins,automation scan

#2316

· ruvnet opened

on Jun 8, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Dream Cycle 2026-06-12] intelligence: Agents-K1 KG gap — flat HNSW ReasoningBank cannot multi-hop; −80% TTFT from interleaved RL + capabilities,memory scan

Daemon self-terminating TTL + global status, honest HNSW/init footguns (carry-forward from pacphi/ruflo-machine-ref)

feat(router): Claude Fable 5 frontier routing tier — design, full change-point map, and a temperature 400 that blocks the entire Opus 4.7/4.8/Fable family today

agent_execute requires its own LLM provider key — should delegate inference to the MCP host (e.g. Codex) via MCP sampling

[Dream Cycle 2026-06-11] security: runtime governance gap — Microsoft AGT forecloses 7 ASI risks at <0.1ms; Ruflo has no policy engine + intelligence,swarm scan

Superseded community PRs are orphaned when their fix merges via a different (batch) PR

[Dream Cycle 2026-06-10] performance: DeLM shared-context +10.5pp SWE-bench gap (−50% cost) + security,hive-mind scan

feat(agents): integrate Claude Code nested-subagent (depth=5) capability — ADR-147

model router: exploring Option B — wire `@ruvector/tiny-dancer` FastGRNN through the now-documented embedding seam (follow-up to #2329)

[Dream Cycle 2026-06-09] swarm: RL orchestration 5-decision gap (no stopping-RL in any framework) + ruview-integration,ruvector-integration scan

[dream-cycle] meta: ADR-147 collision across 6 open PRs + 0 merges in 14 nights

[Dream Cycle 2026-06-08] memory: multi-signal retrieval gap vs Mem0 SOTA (94.4% LongMemEval) + plugins,automation scan

Search results