OPC/synapbus
2
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity
177 Commits 3 Branches 21 Tags
190df8119f75fbf0c751d355554dfaf36b8eadb8
Commit Graph
4 Commits
Author SHA1 Message Date
Algis DumbrisandClaude Opus 4.6 e77fd7afdf spec(017): MuSiQue MAS benchmark harness 
Feature spec for Python benchmark that integration-tests 016 marketplace
against a real multi-hop reasoning task. 4 prioritized user stories:
P1 single-shot Pareto verification, P2 curated trio with dedup,
P3 learning tier, P1 rich HTML report. 23 FRs, 7 success criteria.

Also: brainstorming design doc at docs/superpowers/specs/ capturing
the 6 clarifying questions and chosen decisions (mixed-tier pool,
curated trio, tiered run modes, wait-for-016 execution strategy).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-11 15:02:59 +03:00
Algis DumbrisandClaude Opus 4.6 2b5dc652e7 docs: demo scenarios, gaps analysis, and website redesign spec 
6 demo scenarios from single agent to 4-agent outreach pipeline.
SynapBus as agent memory (channels + semantic search). Three-stage
progression (experiment → stabilize → scale). Identified gaps in
code, website, and documentation. Website restructure proposal.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-22 06:59:35 +02:00
Algis DumbrisandClaude Opus 4.6 1b942db80e docs: agent experimentation environment design spec 
Three-stage progression: experiment (Claude Code + /loop) → stabilize
(git repo + Agent SDK) → scale (Docker/K8s). SynapBus stays runtime
agnostic — downloadable CLAUDE.md per archetype, MCP config snippet,
skills as optional plugins. No Docker or K8s required for Stage 1.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-20 09:45:55 +02:00
Algis DumbrisandClaude Opus 4.6 695dbf0c9f docs: agent platform architecture design spec 
Three-layer architecture (Infrastructure, SynapBus, Agent Instances),
stigmergy coordination via workflow reactions, agent archetypes with
CLAUDE.md specialization, trust scoring, local-first runtime with
docker-compose, agent-init CLI tool, and 10 ensemble work ideas.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-18 19:51:27 +02:00