Persisting Persisting

Persistent infrastructure for the Agent era.

CI Documentation License: Apache-2.0

Persisting logo

Persisting connects durable model state—parameters and KV caches—with durable Agent history—trajectories and execution records. The current product is the path from execution to queryable history:

Governed execution Durable history
pVisor pChronicle
  • pvisor is an executor that produces persistable, reviewable facts: staged Effects and execution records from one Agent Run;
  • pchronicle browses, queries, exchanges, and serves trajectory Datasets.

Each command works on its own. Connected, they cover pvisor run --stage … → review/apply → configured capture → a queryable Dataset.

Current Persisting workflows and the execution-to-history throughline

Install

pip install persisting[lance]
pvisor --version
pchronicle --version

The rolling nightly build installs the same commands without a Rust toolchain:

curl -fsSL https://raw.githubusercontent.com/DeepLink-org/Persisting/main/scripts/install-nightly.sh | bash

See the installation guide for platform requirements and executor setup.

Run one Agent and review its changes

pvisor run --stage ./runs/task-001 -- codex
pvisor review last
pvisor apply last --all   # or: pvisor drop last

--stage creates a copy-on-write workspace view for review; without it the Agent may write the real project tree. The exact boundary is platform-dependent and recorded with the Run—consult the execution guide before treating it as a security boundary.

Query Agent trajectory history

pchronicle onboard
pchronicle onboard query
pchronicle agent codex ./trajectory-data --ask "Which tools fail most often?"

The onboarding flow creates a temporary example Dataset—no source checkout required. pchronicle import accepts ATIF, ACTF, and OpenAI Messages; pchronicle serve starts a loopback-only, read-only Dataset UI and API.

After capture is configured, selected pVisor Run events can enter a pChronicle Dataset. See the capture guide.

Current maturity

Capability Status
pVisor host execution, review, checkpoints, and transactional workspace Implemented
pChronicle local/S3 catalog, bounded SQL, analysis, find, import/export Implemented
pChronicle loopback-only read API and embedded Web UI Implemented
Gateway capture and cooperative proxy policy Implemented
Container/libkrun executors and transparent network boundaries Platform-dependent; see the pVisor and OverlayNet docs
Queue and document Search Separate stable capabilities
Tensor Memory / TTAS Experimental

Documentation

Criterion.rs microbenchmarks and hyperfine lifecycle scenarios are compared against main in CI; see the benchmark contract.

Latest nightly pChronicle benchmark: d628946b6ac4 on linux/x86_64 (2026-09-11T11:26:09.379341+00:00).

Case Metric Value
criterion/atif_conversion/parse_corpus latency_median_ns 5.536e+06 ns
criterion/atif_conversion/roundtrip_corpus latency_median_ns 7.369e+06 ns
criterion/projection_cpu/events_to_storyline_corpus latency_median_ns 3.408e+05 ns
system/projection_pipeline/event_append initial_append_ms 71.601 ms
system/projection_pipeline/projection_build build_ms 5390.446 ms
system/projection_pipeline/projection_incremental sync_ms 39.511 ms
system/lance_vs_json/lifecycle cold_query_ms 2933.682 ms
system/lance_vs_json/lifecycle get_storyline_full_ms 9.724 ms
system/lance_vs_json/lifecycle replace_storyline_ms 42.659 ms
system/lance_vs_json/selective lance_qps 347 ops/s
system/lance_vs_json/group_by lance_qps 447.1 ops/s
system/lance_vs_json/summary lance_over_json 0.244 ratio
system/json_streaming_ndjson/json_streaming p95_ms 14.444 ms
system/json_streaming_ndjson/json_streaming rows_s 2.744e+05 ops/s
system/json_streaming_ndjson/json_streaming process_peak_rss_mib 45.492 MiB
hyperfine/projection_pipeline wall_median_seconds 5.577 s
hyperfine/lance_vs_json wall_median_seconds 39.863 s

Open the complete benchmark run.

License

Apache License 2.0. See NOTICE for third-party attributions and separately licensed bundled components.

Project links

Data verified by PyPI on Sep 11, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for reiase from gravatar.com reiase

Credits

Author: reiase

GitHub Statistics

Data verified by PyPI on Sep 11, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

Apache-2.0
View SPDX License List

Requires

Python >=3.10

Provides Extra

lance all dev

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

persisting-0.3.0-py3-none-manylinux_2_28_x86_64.whl (61.0 MB view details)

Uploaded Python 3manylinux: glibc 2.28+ x86-64

persisting-0.3.0-py3-none-macosx_11_0_arm64.whl (63.7 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

File details

Details for the file persisting-0.3.0-py3-none-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for persisting-0.3.0-py3-none-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 34da8f6fa78d3b1cd8ec1f3f31339f7198714c166e1c5eafe62147dd881069ca
MD5 df5e2d350dda45a6d8ce8c1e9dce7f8a
BLAKE2b-256 12e28611582761eaf504dcd78fb776466434f433e33ce92258e7612c80121bc3

See more details on using hashes here.

Provenance

The following attestation bundles were made for persisting-0.3.0-py3-none-manylinux_2_28_x86_64.whl:

Publisher: release.yml on DeepLink-org/Persisting

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file persisting-0.3.0-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for persisting-0.3.0-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 9bc3c8fdf79e7824de3c91a3143cf195446d23b6fdf79a774d8f3d4e0335e65c
MD5 c3747755a7d406d4d3fcbc2711ab45b9
BLAKE2b-256 8d04ba3d90a9fb69c0ac2260134084e50d025948bd9f168bc18ae67f2d963188

See more details on using hashes here.

Provenance

The following attestation bundles were made for persisting-0.3.0-py3-none-macosx_11_0_arm64.whl:

Publisher: release.yml on DeepLink-org/Persisting

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.3.0 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page