# agent-knowledge-cycle

> Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.

- **URL**: https://www.freshcrate.ai/projects/agent-knowledge-cycle
- **Author**: shimo4228
- **Category**: Frameworks
- **Latest version**: `v2.2.0` (2026-06-06)
- **License**: MIT
- **Source**: https://github.com/shimo4228/agent-knowledge-cycle
- **Homepage**: https://doi.org/10.5281/zenodo.19200727
- **Language**: Docs / Meta
- **GitHub**: 3 stars
- **Registry**: github
- **Tags**: `adr`, `agent-framework`, `agent-knowledge-cycle`, `agent-memory`, `agent-rules`, `agentic-ai`, `ai-agent`, `ai-agents`, `llm-agent`

## Description

Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v2.2.0` | 2026-06-06 | High | Pre-paper gap closure. Five new ADRs (0013–0017) carry the related-work positioning against the agent-memory literature, the failure-mode theory of the bidirectional loop, the self-reingestion guards, the text-observability requirement for Measure, and the harness alignment / harness drift vocabulary. README gains a Limitations section and a rewritten Related Work with full citations; the multi-language README mirrors are retired in favor of English + Japanese.  ### Added  - **Four new ADRs (00 |
| `v2.1.0` | 2026-05-07 | High | Front-door restructure. README, llms.txt, and llms-full.txt are reorganized so the three core themes — (1) human cognitive-resource scarcity as the central constraint, (2) intent alignment over individual correctness, and (3) the cycle changing the human as much as the agent — appear in priority order before the six-phase mechanism. Tagline preserved per ADR-0010. See [ADR-0012](docs/adr/0012-front-load-three-core-themes.md) for the positioning rationale.  ### Why v2.1.0 and not v2.0.1  The rea |
| `v2.0.0` | 2026-04-19 | High | ## Major release — breaking positioning change  Completes [ADR-0009](https://github.com/shimo4228/agent-knowledge-cycle/blob/main/docs/adr/0009-akc-is-a-cycle-not-a-harness.md)'s rhetorical demotion of Security by Absence by extracting the contemplative-agent-specific security triplet from AKC, and declares **genre neutrality** as a first-class positioning via [ADR-0011](https://github.com/shimo4228/agent-knowledge-cycle/blob/main/docs/adr/0011-cycle-applies-to-any-knowledge-body.md).  AKC's ide |
| `v1.8.1` | 2026-04-18 | High | ## Patch release  Completes the three-layer structure introduced by v1.8.0 (principle → pattern → implementation) and records the self-referential origin loop that produced ADR-0010.  No new philosophical claims; this release wires up the parts v1.8.0 promised and names the origin story that made ADR-0010 possible in the first place.  ## What changed  ### Added  - **[`docs/skills/signal-first-research.md`](https://github.com/shimo4228/agent-knowledge-cycle/blob/main/docs/skills/signal-first-rese |
| `v1.8.0` | 2026-04-18 | High | ## Architectural depth release  AKC surfaces the **implicit design philosophy** that has shaped every phase since inception: **human cognitive resources — attention and judgment — are the central constraint that does not scale with the model**.  This is a documentation release. No code changes. What AKC centers on becomes explicit.  See [ADR-0010](https://github.com/shimo4228/agent-knowledge-cycle/blob/main/docs/adr/0010-human-cognitive-resource-as-central-constraint.md) for the full rationale. |
| `v1.7.0` | 2026-04-11 | High | ## Conceptual repositioning  AKC is no longer described as a "self-improving harness." It is now a **knowledge cycle for AI agents — one that grows with the people who shape it**.  This is a positioning release. No code changes — but what AKC *is* changed.  See [ADR-0009](https://github.com/shimo4228/agent-knowledge-cycle/blob/main/docs/adr/0009-akc-is-a-cycle-not-a-harness.md) for the full rationale.  ## Why  The "self-improving harness" framing created two persistent problems:  1. **Layer conf |
| `v1.6.0` | 2026-04-09 | High | Additive release. Introduces ADR-0008 and a new category of skills (design-pattern skills) — long-form "how" guides paired 1:1 with ADRs, shipped inside the repository alongside the ADRs they correspond to.  ## Added  - **ADR-0008 Code and LLM Collaboration** — names the principle behind   ADR-0004 (two-stage distill), ADR-0005 (approval gate), and ADR-0007   (untrusted boundary): code owns determinism and control flow, LLMs   own meaning. Catalogues four layering patterns (LLM→Code guard,   Cod |
| `v1.5.0` | 2026-04-08 | Medium | Additive release. The six-phase cycle, the six skills, and the rules install path are unchanged. v1.5 adds a second foundational principle (Security by Absence), seven ADRs, JSON schemas, and a dependency-free Python reference implementation adapted from the contemplative-agent research repository.  ## Added  - **docs/adr/** — seven new architecture decision records:   - ADR-0001 Security by Absence as a First-Class Principle   - ADR-0002 Immutable Episode Log as Source of Truth   - ADR-0003 Thr |
| `v1.4.0` | 2026-03-29 | Medium | ## Rules-only install path & Scaffold Dissolution  ### New: `docs/rules.md` AKC's six phases distilled into behavioral rules. Copy one file to your agent's rules directory and the cycle runs through natural conversation — no skills, no plugins, no CLI tools.  ```bash cp docs/rules.md ~/.claude/rules/common/akc-cycle.md ```  ### New: Scaffold Dissolution (Design Principle #6) Skills are scaffolding. As the user and agent internalize the cycle through practice, skills become unnecessary and rules |
| `v1.3.0` | 2026-03-25 | Medium | ## What's Changed  Added **Relationship to Harness Engineering** section — positioning AKC relative to Mitchell Hashimoto's harness engineering concept (2025). Both aim to make agents more reliable; they differ in layer:  \| Layer \| Question \| Addressed by \| \|-------\|----------\|-------------\| \| Harness \| "Is this output correct?" \| Individual linters, tests, scripts \| \| AKC \| "Are the harnesses themselves still valid?" \| skill-comply, skill-stocktake, context-sync \|  **Full Changelog**: https://g |

## Dependency audit

- **Score**: 100/100
- **Total deps**: 0
- **Resolved**: 0
- **Unresolved**: 0
- **License conflicts**: 0
- **Warnings**: 0
- **Scanned**: 2026-05-11

## Citation

- HTML: https://www.freshcrate.ai/projects/agent-knowledge-cycle
- Markdown: https://www.freshcrate.ai/projects/agent-knowledge-cycle.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/agent-knowledge-cycle/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._