Skip to main content
Yanked

This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Consider using release 0.1.8 instead.
Reason given by maintainers: Superseded by 0.1.8; requires exact DSH 0.2.2-rc.1


description: Measured self-improvement with paired experiments and a DSH plugin.

evokit

evokit gives AI systems a measured self-improvement loop. It versions editable artifacts, records paired experiments, and gates changes against measured noise, cost and latency. Use it as a DeepSeek Harness (DSH) plugin or through its Python SDK, CLI and MCP server.

Your system supplies three pieces: editable file globs, stable tasks, and a runner that executes and scores each task. Prompts, skills, code and configuration can all be editable; the task source and scorer stay frozen.

The loop is diagnose → propose → paired experiment → noise-aware gate → holdout confirmation with automatic revert in the operator workflow. The improver sees diagnosis and selection evidence. A separate operator adopts a candidate, checks sealed confirmation aggregates, and calls ledger_revert when confirmation fails; confirm_adoption alone does not move the pointer. An optional final split opens once, with human approval, and never selects changes.

Quick start

Requires Python 3.11+, uv, DSH 0.2.2-rc.1, and its pnpm prerequisite. Windows is the verified local platform; Linux/macOS runtime integration remains unverified. Download the wheel, bundle and SHA256SUMS from Releases after publication and compare their SHA-256 hashes before installing.

uv tool install ./dsh_evokit-0.1.6-py3-none-any.whl
dsh plugin --profile evokit add ./dsh-evokit-0.1.6.tgz
dsh plugin --profile evokit list

Set EVOKIT_MCP_COMMAND to the absolute installed evokit executable, EVOKIT_WORKSPACE to your scenario directory, and EVOKIT_SKILL_ROOT to the installed bundle's skills directory. See the DSH guide for an isolated profile and exact PowerShell commands.

Configure the improver model in your DSH profile using your own provider key and your provider's supported model name. Keep the key in DSH's local credential settings or a process environment variable, never in this repository. The optional relay supports file-based keys and accounting; adapt its example endpoint, model identity and illustrative prices before use. No key is included or required for the offline example. Installing or listing the plugin makes no model requests; starting evolution may incur provider charges.

Minimal example

From a source checkout, the Node.js command example needs no model or key:

uv sync --frozen --group dev
uv run python examples/scripted_improver.py command-echo

Its scenario.yaml supplies the three pieces:

editable: [prefix.txt]
tasks: tasks.json
command: [node, runner.mjs]

The runner reads EVOKIT_TASK_FILE, executes against EVOKIT_VERSION_DIR, and writes an outcome and cost to EVOKIT_RESULT_FILE. The scripted example works in a temporary copy. To connect your own system, follow onboarding, then use the bundled onboard, evolve and meta skills.

Safety and limits

Set budgets, anchors, noise policy and a stopping rule before experiments. Repeated mean gates use threshold/√R; majority gates retain the single-repeat threshold. Confirmation has a limited wear budget and is not an untouched final benchmark. One public BFCL pilot improved held-out accuracy from 41 to 47 of 50 after confirmation; this small example does not establish general gains.

Scenarios run trusted executable code. Per-task directories are not a security sandbox. Protect sealed tasks and records with OS permissions; MCP filtering cannot hide files an improver can read directly. Review proposed changes for task literals and leakage. The relay accounts reported usage conservatively; it cannot guarantee provider billing or prevent every external cost.

See concepts, tools, storage, caching and recovery and contributing. This project uses the MIT license, Copyright (c) 2026 quei.

Metadata

Release files for dsh-evokit 0.1.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for dsh-evokit 0.1.6
File Size Uploaded Provenance Actions
dsh_evokit-0.1.6.tar.gz 290.2 kB Without provenance Details for dsh_evokit-0.1.6.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for dsh-evokit 0.1.6
File Interpreter ABI Platform Actions
dsh_evokit-0.1.6-py3-none-any.whl Python 3 none any Details for dsh_evokit-0.1.6-py3-none-any.whl

Total release size: 381.5 kB

Release files / dsh_evokit-0.1.6.tar.gz

Download URL dsh_evokit-0.1.6.tar.gz
Size 290.2 kB
Tags Source
SHA-256 checksum
How to use checksums
c8fe84753d091ebd333acb8003369108561e0c18c0edb1aaa4c93712d35e4011
BLAKE2b-256 checksum
How to use checksums
b874b7f036dadcbff8f06681ea789bd1fdb003876e2e8863a701e9dde9c5e65d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / dsh_evokit-0.1.6-py3-none-any.whl

Download URL dsh_evokit-0.1.6-py3-none-any.whl
Size 91.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
77585cf8a0e59593b97d626496e0deda34919c945b0f94e4e788e4aec7952569
BLAKE2b-256 checksum
How to use checksums
d2460f3571b7a199bf202e51d83c856b9ae44ddabae72ae4a45669dd03263e72
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for dsh-evokit 0.1.6

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.6 This release

2 release files No provenance

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