# KaizenAgentic Ecosystem Assessment **Date:** 2026-06-16 **Compared repos:** info-tech-canon, agentic-resources, activity-core, llm-connect, identity-canon, phase-memory, artifact-store, domain-tree, kontextual-engine, tele-mcp **Against:** `INTENT.md`, `wiki/`, WP-0003 measurement loop plan --- ## Strategic Insight INTENT's vision is **distributed across the ecosystem**, not missing from a single repo: | INTENT promise | Primary owner | |----------------|---------------| | Agent definitions + deployment | kaizen-agentic | | Project memory + Coach | kaizen-agentic | | Per-agent metrics + optimizer | kaizen-agentic (WP-0003) | | Session capture + fleet metrics | agentic-resources (Helix Forge) | | Scheduled improvement triggers | activity-core | | Evidence retention | artifact-store | | Rich memory graphs | phase-memory (future) | | Guidance as knowledge | kontextual-engine + info-tech-canon | | Semantic vocabulary | info-tech-canon, identity-canon | | Org placement | domain-tree | | Runtime telemetry MCP | tele-mcp (unassessed — not cloned) | KaizenAgentic matures by **stabilizing conventions and composing adjacent services**, consistent with INTENT boundaries. --- ## Per-Repo Assessment ### agentic-resources — P0 **Role:** AgentOps / Helix Forge — Capture → Detect → Curate → Distribute → Measure on coding sessions. **Use:** Fleet-level session metrics (`session_memory/measure/`), JSONL baselines, cross-agent adapters (Claude/Codex/Grok). Complements project-scoped `.kaizen/metrics/`. **Action:** ADR-004 correlation fields; WP-0004 integration; do not re-implement session ingestion here. ### activity-core — P1 **Role:** Event bridge — cron/NATS → task emission. **Use:** Scheduled `metrics optimize`, retention hygiene, metrics scaffold validation after agent install. **Action:** WP-0004 ActivityDefinitions after WP-0003 Part 2. ### artifact-store — P1 **Role:** Artifact registry + retention gateway. **Use:** Persist optimizer `analysis.json`, recommendations, e2e evidence packages. **Action:** WP-0004 pilot registration with `raw-evidence` retention class. ### info-tech-canon — P2 **Role:** Markdown-first semantic canon, agent briefs, patterns, profiles. **Use:** Map KaizenAgentTemplate → canon profiles; publish per-agent briefs; validation rules for `kaizen-agentic validate`. **Action:** WP-0004 Part 4 (later phase). ### phase-memory — P2 **Role:** Profile-driven memory graphs (ephemeral → rigid). **Use:** Upgrade path from flat `.kaizen/agents/*/memory.md`. **Action:** Future WP after WP-0004; no WP-0003 blocker. ### kontextual-engine — P2 **Role:** Knowledge operations engine. **Use:** Ingest `wiki/` and `agents/` as knowledge assets; KaizenGuidance catalog runtime. **Action:** WP-0004 Part 4 (guidance pilot). ### llm-connect — P3 **Role:** Provider-neutral LLM adapter. **Use:** Automated Coach/optimizer narration when LLM synthesis moves beyond CLI context assembly. **Action:** Reference pattern; adopt when WP-0003+ adds LLM-powered recommendations. ### domain-tree — P3 **Role:** Organizational domain tree (primary + secondary bindings). **Use:** Register kaizen-agentic and agent categories in org structure. **Action:** When capability catalog matures. ### identity-canon — P3 **Role:** Identity/agent terminology research. **Use:** Distinguish agent persona vs instance vs session actor for "digital talent agency" framing. **Action:** Glossary alignment in wiki. ### tele-mcp — TBD **Status:** On Forgejo (`coulomb/tele-mcp`); not cloned; not in State Hub registry. Name suggests telemetry MCP. **Action:** Clone and assess before integration; candidate for WP-0001 T04 telemetry adapter. --- ## Two-Layer Measurement Model | Layer | Scope | Owner | Storage | |-------|-------|-------|---------| | **Fleet** | Cross-repo session outcomes | agentic-resources | Helix Forge store + `measure/baselines.jsonl` | | **Project** | Per-agent persona performance in one repo | kaizen-agentic | `.kaizen/metrics//executions.jsonl` | Correlation via shared fields defined in ADR-004 (`helix_session_uid`, `repo`, `success`, `tokens`, `execution_time_s`). See `wiki/EcosystemIntegration.md` for integration contracts. --- ## Priority Matrix | Priority | Repo | WP | |----------|------|-----| | P0 | agentic-resources | WP-0004 Part 1 | | P1 | activity-core | WP-0004 Part 2 | | P1 | artifact-store | WP-0004 Part 3 | | P2 | info-tech-canon, kontextual-engine, phase-memory | WP-0004 Part 4 / future | | P3 | llm-connect, domain-tree, identity-canon | Adopt as needed | | TBD | tele-mcp | Assess when cloned | --- ## Follow-Up Workplans - **KAIZEN-WP-0003** — measurement loop (completed 2026-06-18) - **KAIZEN-WP-0004** — ecosystem integration (completed 2026-06-18) --- ## WP-0004 Outcomes (2026-06-18) ### Part 1 — Helix Forge correlation - `HELIX_SESSION_UID` env auto-merge on `metrics record` - `kaizen-agentic metrics correlate ` read-only adapter (sqlite or stub) - Contract: `docs/integrations/helix-forge-correlation.md` - Worked example in `wiki/EcosystemIntegration.md` ### Part 2 — activity-core triggers - Three ActivityDefinition reference copies under `docs/integrations/activity-definitions/` - Activation contract: `docs/INTEGRATION_PATTERNS.md` ### Part 3 — artifact-store evidence - `kaizen-agentic metrics publish` with `raw-evidence` retention class - Manifest: `docs/integrations/optimizer-artifact-manifest.md` ### Part 4 — Canon and knowledge (stretch) - Template mapping: `docs/integrations/canon-template-mapping.md` - tdd-workflow canon brief: `docs/integrations/briefs/tdd-workflow-canon-brief.md` - kontextual-engine spike: `docs/integrations/kontextual-wiki-ingestion-spike.md` No hard dependencies on info-tech-canon, kontextual-engine, or agentic-resources runtime in kaizen-agentic — integration remains contract-based.