kaizen-agentic/registry/capabilities/capability.agents.kaizen-framework.md
tegwick 11fa383817
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 2s
ci / test (push) Successful in 2m10s
docs: align execution handoff with Glas
2026-08-21 08:30:13 +02:00

134 lines
4.7 KiB
Markdown

---
id: capability.agents.kaizen-framework
name: Kaizen Agentic Framework
summary: AI agency framework providing 20 deployable agent instruction sets, project memory,
metrics, role and engagement contracts, and scheduled preparation for governed execution.
owner: kaizen-agentic
status: draft
domain: agents
tags:
- agents
- memory
- coordination
- metrics
- scheduling
- engagements
maturity:
discovery:
current: D3
target: D5
confidence: medium
rationale: README, SCOPE, ADRs, and integration contracts document the agent library, memory,
metrics, scheduling, role and engagement surfaces, and versioned release v1.4.0; CI is present.
availability:
current: A2
target: A3
confidence: medium
rationale: Installable via `git clone` + `make setup-complete` + `make agents-install-cli`, with both
source and global installation paths documented; pyproject-packaged.
external_evidence:
completeness:
level: C1
confidence: low
basis: scope_vs_intent_and_consumer_expectations
satisfied_expectations:
- 20 specialized agent instruction sets
- persistent project-scoped agent memory
- Coach meta-agent for fleet-wide pattern synthesis
- project metrics and optimizer workflow
- role packages and file-backed client engagements
- schedule validation and offline execution-bundle preparation
broken_expectations: []
out_of_scope_expectations: []
reliability:
level: R0
confidence: low
basis: consumer_quality_signals
known_reliability_risks:
- downstream execution depends on activity-core, glas-harness, and selected-rein contracts outside this repository
discovery:
intent: Let agents arrive informed, work within explicit roles and engagement boundaries,
and improve through project memory, execution evidence, and governed scheduling contracts.
includes:
- 20 specialized agent instruction sets
- persistent memory and coordination framework
- Coach meta-agent pattern synthesis
- project execution metrics and optimizer artifacts
- role packages and forward-deployed engagement lifecycle helpers
- repo-local schedule manifests and offline preparation bundles
excludes:
- the underlying LLM inference itself (agents are instruction sets, not a model)
assumptions: []
use_cases: []
research_memos: []
availability:
current_level: A2
target_level: A3
current_artifacts:
- Python package (`kaizen-agentic`) v1.4.0
- CLI (`kaizen-agentic`)
- versioned role, engagement, metrics, protocol, and schedule contracts
target_artifacts: []
consumption_modes:
- cli
- library import
- file contracts
relations:
depends_on: []
supports: []
related_to: []
evidence:
documentation:
- README.md
tests:
- tests/
- .forgejo/workflows/
consumer_feedback: []
bug_reports: []
incidents: []
consumer_guidance:
recommended_for:
- projects wanting a deployable, memory-persistent agent fleet with cross-agent coordination
- governed runtimes needing offline agent orientation and schedule preparation contracts
not_recommended_for:
- needs for a single stateless agent (framework overhead not justified)
known_limitations:
- this package prepares work but does not schedule, authorize, or invoke an LLM
- production reliability telemetry is not yet sufficient for a higher reliability rating
promotion_history: []
---
# Kaizen Agentic Framework
## Overview
`kaizen-agentic` is an AI agency framework: 20 specialized agents deployable into any project, each gaining persistent project-scoped memory and coordination through a Coach meta-agent that synthesises fleet-wide patterns and briefs incoming agents.
## Assessment notes
### Discovery
README documents the agent library, the agency framework (persistent memory, Coach meta-agent synthesising fleet-wide patterns), and a versioned release (v1.4.0); has .forgejo/workflows CI.
### Availability
Installable via `git clone` + `make setup-complete` + `make agents-install-cli`, with both source and global installation paths documented; pyproject-packaged.
### Completeness
First-pass honest assessment from the REUSE-WP-0017 coverage campaign
(reuse-surface). No external consumer feedback exists yet; levels reflect
scope-vs-intent documentation quality, not internal code quality.
### Reliability
No production consumer telemetry exists yet; reliability level is
intentionally conservative pending REUSE-WP-0019 reuse-telemetry evidence.
## Promotion checklist
- [x] ID follows `capability.<domain>.<name>` pattern
- [x] Maturity enums match `specs/CapabilityMaturityStandard.md`
- [x] `external_evidence` is populated separately from `maturity`
- [ ] Relations reference valid capability IDs (none yet)
- [x] Index entry added in `registry/indexes/capabilities.yaml`