Metadata-Version: 2.4
Name: ai-agent-persistence
Version: 0.1.1
Summary: Evidence-first tools for validating AI agent persistence publications and probing durable state serialization
Author: Chris / SaientAI
License-Expression: MIT
Project-URL: Homepage, https://saient.co.uk/agent-persistence
Project-URL: Paper, https://saient.co.uk/agent-persistence
Project-URL: PDF, https://saient.co.uk/downloads/ai-agent-persistence-paper.pdf
Project-URL: Source, https://github.com/SaientAI/ai-agent-persistence
Project-URL: Issues, https://github.com/SaientAI/ai-agent-persistence/issues
Keywords: ai-agents,persistence,memory,evaluation,reproducibility
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Testing
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# AI Agent Persistence

## Persistence Without Mystification

An evidence-first case study of memory, goal continuity, checkpointing, and long-horizon agency in the Saient projects.

The central finding is simple: **AI persistence is not one property**. It is a stack of engineering mechanisms with different failure modes:

1. process-local computational reuse;
2. durable state;
3. episodic and semantic recall;
4. task and workspace continuity;
5. bounded goal continuity; and
6. operational continuity.

The Saient work implements meaningful parts of this stack. It does **not** establish consciousness, a continuous subjective identity, or the unconstrained creation of goals “from nowhere.” Earlier experiments that appeared to support the strongest goal-origin claim are examined here as valuable negative results.

## Read the paper

- [Canonical HTML paper on saient.co.uk](https://saient.co.uk/agent-persistence)
- [Print-ready PDF](https://saient.co.uk/downloads/ai-agent-persistence-paper.pdf)
- [Full paper](https://github.com/SaientAI/ai-agent-persistence/blob/main/paper/PERSISTENCE_WITHOUT_MYSTIFICATION.md)
- [Claim ledger](https://github.com/SaientAI/ai-agent-persistence/blob/main/evidence/CLAIM_LEDGER.md)
- [Reproduction record](https://github.com/SaientAI/ai-agent-persistence/blob/main/evidence/REPRODUCTION.md)
- [Source and privacy inventory](https://github.com/SaientAI/ai-agent-persistence/blob/main/evidence/SOURCE_INVENTORY.md)
- [Aggregate V4 rerun result](https://github.com/SaientAI/ai-agent-persistence/blob/main/evidence/v4-rerun-summary.json)
- [Verifier-bait audit summary](https://github.com/SaientAI/ai-agent-persistence/blob/main/evidence/verifier-bait-audit.md)

## What was verified on 29 August 2026

- The current Saient Python suite passed **418 tests**.
- The desktop checkpoint, memory-store, and lifecycle subsets passed **14**, **7**, and **2** Rust tests respectively.
- A 32-process test against the bundled runtime finished with a valid state file and final tick **32**.
- The archived V4 objective-genesis harness reproduced its operational score: **100/100 seeds passed** and every seed reasserted the selected objective six times.
- That V4 result does not demonstrate unconstrained objective genesis: the canonical command did not enable its optional LLM proposer; objectives came from a fixed vocabulary and trajectory templates; and the steering flag directly caused a remembered objective to be proposed and preferred.
- The published corrected verifier-bait dataset passed its structural audit, while preserving important evidence of path sensitivity, criterion editing, and earlier invalid measurements.

These statements have deliberately different scopes. Passing a mechanism test is evidence for that mechanism, not evidence for phenomenology or personhood.

## Public and private source boundary

The desktop application is public at [SaientAI/ai-workshop](https://github.com/SaientAI/ai-workshop). The historical Aria/Saient research repository was private when this report was prepared. This repository therefore publishes claim-level evidence, commands, hashes, commit identifiers, and aggregate results—but not private source code or raw traces that may contain local paths.

## Citation

See [CITATION.cff](https://github.com/SaientAI/ai-agent-persistence/blob/main/CITATION.cff). The paper and tools are licensed under the [MIT License](https://github.com/SaientAI/ai-agent-persistence/blob/main/LICENSE).

## Reproduction note

The exact environments, commands, outputs, limitations, and the mismatch between one historical example and the archived rerun are recorded in the [reproduction record](https://github.com/SaientAI/ai-agent-persistence/blob/main/evidence/REPRODUCTION.md). Start there before treating any result as independently reproducible.

Validate this publication package locally with:

```bash
python3 scripts/validate_publication.py
```

## Installable evaluation tools

The repository also provides dependency-free Python command-line tools:

```bash
python3 -m pip install ai-agent-persistence
ai-agent-persistence validate /path/to/ai-agent-persistence
ai-agent-persistence probe --runtime /path/to/ai-workshop/runtime --processes 32
```

The validator checks the publication's required evidence files, JSON, local
links, duplicate claim identifiers, and common secret or private-path patterns.
The concurrency probe launches simultaneous Saient ticks in an isolated state
directory and verifies that all successful ticks are durably serialized.
