Briefcase AI SDK

License: Apache-2.0

Governance infrastructure for AI decisions: enforce controls, record context, replay later.

Install

pip install briefcase-ai

Quick Example

import briefcase

briefcase.observe("console")          # send records to stderr (or "memory" / "runs.jsonl")

@briefcase.capture(decision_type="classify_text")
def classify(text: str) -> str:
    return text.upper()

classify("hello world")               # a decision record is emitted

capture works immediately — no briefcase.init() required. Call init() only when you use the native runtime features (storage backends, snapshots). Without a call to briefcase.observe(...) (or briefcase.setup(exporter=...)), @capture records decisions but has nowhere to send them.

Exporters. briefcase.observe(...) accepts "console", "memory" (records collected on exporter.records), a "*.jsonl" path, or any briefcase.exporters.BaseExporter instance — subclass BaseExporter to ship records to your own backend.

Evaluations and RL

Two bridges emit decision records from work that is not a single function call. Both use the exporter you already configured.

from briefcase.integrations.evals import EvalRun, from_inspect_log, replay

with EvalRun("gsm8k", model="claude-opus-5") as run:   # one eval.case per case,
    run.log_case("q1", inputs=q, outputs=a, passed=a == target)   # one eval.run
print(run.summary()["pass_rate"])

replay(from_inspect_log("logs/2026-08-12_gsm8k.eval"))  # inspect-ai .json/.eval

The parsers are stdlib only and never import the eval framework, so a log can be replayed on a machine that has neither installed. See examples/eval_runs/.

from briefcase.integrations.gym import GuardrailGymEnv, capture_episodes

env = GuardrailGymEnv(guardrail, tasks, injections)  # a guardrail as a gym.Env
env = capture_episodes(env)                          # rl.step / rl.episode records

Needs pip install briefcase-ai[gym]. See examples/rl_gym/.

capture_episodes exports on a background thread by default, since step capture is on the hot path. A script that exits right after close() can lose its records; pass capture_episodes(env, async_capture=False) in short runs. EvalRun already defaults to async_capture=False for that reason.

Logging

The library is silent by default (it installs only a NullHandler). Turn on visible logs explicitly:

import briefcase
briefcase.enable_logging("DEBUG")     # or set BRIEFCASE_LOG_LEVEL=DEBUG

Using with AI tools (Cursor, Claude Code, Codex, …)

This repo ships machine-readable usage guidance: llms.txt / llms-full.txt, an AGENTS.md, and copy-paste editor rules under docs/llm/. An MCP server is available via pip install briefcase-ai[mcp] then briefcase-mcp.

Extras

Extra	Description
`replay`	Deterministic replay engine for recorded decisions
`drift`	Drift scoring and cost calculation for model outputs
`sanitize`	Built-in PII redaction utilities
`otel`	OpenTelemetry helpers
`storage`	Rust-backed SQLite storage engine
`validate`	Prompt validation engine
`guardrails`	Guardrail framework, wrappers, and registries
`rag`	Versioned embedding pipeline and instrumented retrieval
`rag-chroma` / `rag-pinecone` / `rag-weaviate`	Vector-store adapters (each adds its client)
`correlation`	Workflow and trace correlation helpers
`external`	External data snapshot tracking
`events`	Structured event type and emitter interface
`kafka` / `webhook` / `gcp-logging`	Event transports and the Cloud Logging exporter (webhook is stdlib)
`routing`	Router protocol, agent router, versioned policy registry
`opa`	OPA HTTP router with cached decisions and internal-router fallback (adds `httpx`)
`lakefs`	lakeFS versioned storage client, branch manager, lineage, staged commits
`vcs`	VCS client base protocol plus DVC, Nessie, Pachyderm, ArtiVC, DuckLake, Iceberg, and git-LFS adapters
`vcs-dvc` / `vcs-pachyderm` / `vcs-ducklake` / `vcs-iceberg`	Per-provider VCS clients (the rest are HTTP/subprocess based)
`gym`	Gymnasium bridge: guardrail env adapter and RL episode capture
`evals`	Eval-harness bridge: `EvalRun` logger, inspect-ai / lm-eval parsers (adds `zstandard` for `.eval` archives on Python < 3.14)
`bitemporal`	Bitemporal evidence store, as-of views, append-only corrections
`bitemporal-iceberg`	pyiceberg-backed bitemporal store (any supported catalog)
`bitemporal-glue`	AWS Glue catalog auth for the Iceberg backend (adds `boto3`)
`kdb`	kdb+ bitemporal backend (adds KX-licensed `pykx`; excluded from `all`)
`compliance`	Examiner bundles joining decision, evidence, and policy version
`compliance-kms`	KMS-signed examiner bundles against your own AWS KMS key (adds `boto3`)
`controls`	Gateway, quota, throttle classification, and retry (no extra dependencies)
`integrity`	Tamper-evident hash chains, canonical JSON, Ed25519 signing over digests and JSON manifests (signing adds `pynacl`)
`langchain` / `crewai` / `llamaindex` / `autogen` / `ag2` / `pageindex` / `openai-agents`	Framework auto-instrumentation via `briefcase.auto` (each adds its framework)
`mcp`	MCP server (`briefcase-mcp`) exposing the SDK to AI agents
`dev`	Dev tooling: pytest, mypy, flake8, moto
`all`	Installs every optional extra listed above except `kdb`

Most features are native- or pure-Python-backed and ship with the base package — their extras (replay, drift, sanitize, storage, routing, bitemporal, compliance, …) are convenience groupings that pull in no additional dependencies. The extras that install third-party packages are otel, lakefs, bitemporal-iceberg, bitemporal-glue, kdb, compliance-kms, gym, evals, mcp, opa, kafka, gcp-logging, integrity, the rag-* and vcs-* store adapters, and the framework auto-instrumentation extras.

Managed platform

Every library feature runs against infrastructure you own: storage backends (in-memory, SQLite, pyiceberg, Glue-authenticated Iceberg, kdb+), KMS-signed examiner bundles, guardrails, RBAC/ABAC/OPA policy evaluation, routing, replay, framework auto-instrumentation (briefcase.auto), lakeFS branching and lineage, vector-store and VCS adapters, event transports, and the controls layer, in both Python and TypeScript (@briefcase-ai/controls).

The commercial offering is the hosted platform, not gated code: a managed control plane, catalog provisioning and credential brokering, operational runbooks (DR failover, catalog migration, key rotation), certified retention and regulator attestations, licensed market-data ingest (Bloomberg BPIPE, Refinitiv, ICE), and SOC 2 / FedRAMP posture with SLA support.

Contact sales@briefcasebrain.com for the managed platform.

Telemetry

The SDK can report anonymous usage metrics (SDK version, OS, architecture, backend type) to help prioritize development. No personal data or decision content is ever collected. Telemetry is only transmitted when a collection endpoint is configured via BRIEFCASE_API_URL (it defaults to localhost, i.e. a no-op), and you can disable it entirely at any time:

export BRIEFCASE_TELEMETRY=0   # also accepts: false, no, off (case-insensitive)

Links

Docs: briefcaseai.io
GitHub: github.com/briefcasebrain/briefcase-ai-sdk
Contributing: CONTRIBUTING.md

ag2 all autogen bitemporal bitemporal-glue bitemporal-iceberg compliance compliance-kms controls correlation crewai dev drift evals events external gcp-logging guardrails gym integrity kafka kdb lakefs langchain llamaindex mcp opa openai-agents otel pageindex rag rag-chroma rag-pinecone rag-weaviate replay routing run sanitize storage validate vcs vcs-ducklake vcs-dvc vcs-iceberg vcs-pachyderm webhook

Download files

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

Source Distribution

briefcase_ai-4.3.0.tar.gz (335.5 kB view details)

Uploaded Aug 16, 2026 Source

Built Distributions

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

briefcase_ai-4.3.0-cp39-abi3-win_amd64.whl (7.6 MB view details)

Uploaded Aug 16, 2026 CPython 3.9+Windows x86-64

briefcase_ai-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.3 MB view details)

Uploaded Aug 16, 2026 CPython 3.9+manylinux: glibc 2.17+ x86-64

briefcase_ai-4.3.0-cp39-abi3-macosx_11_0_arm64.whl (7.9 MB view details)

Uploaded Aug 16, 2026 CPython 3.9+macOS 11.0+ ARM64

briefcase_ai-4.3.0-cp39-abi3-macosx_10_12_x86_64.whl (8.0 MB view details)

Uploaded Aug 16, 2026 CPython 3.9+macOS 10.12+ x86-64

File details

Details for the file briefcase_ai-4.3.0.tar.gz.

File metadata

Download URL: briefcase_ai-4.3.0.tar.gz
Upload date: Aug 16, 2026
Size: 335.5 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for briefcase_ai-4.3.0.tar.gz
Algorithm	Hash digest
SHA256	`3276d9300f655631d6499fb89a76f44a1873b00eede152a271708eb56983bf84`
MD5	`8fae386f3108581990a4571c2d545b35`
BLAKE2b-256	`5a6b36fad5747e65a7abe7f9d6819a8d81049d187b9306b38224923418e7f8b4`

See more details on using hashes here.

Provenance

The following attestation bundles were made for briefcase_ai-4.3.0.tar.gz:

Publisher: publish.yml on briefcasebrain/briefcase-ai-sdk

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: briefcase_ai-4.3.0.tar.gz
- Subject digest: 3276d9300f655631d6499fb89a76f44a1873b00eede152a271708eb56983bf84
- Sigstore transparency entry: 2492980432
- Sigstore integration time: Aug 16, 2026
Source repository:
- Permalink: briefcasebrain/briefcase-ai-sdk@858b1320f683b2ab4bcfe7f1664df293457e0518
- Branch / Tag: refs/heads/main
- Owner: https://github.com/briefcasebrain
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@858b1320f683b2ab4bcfe7f1664df293457e0518
- Trigger Event: workflow_dispatch

File details

Details for the file briefcase_ai-4.3.0-cp39-abi3-win_amd64.whl.

File metadata

Download URL: briefcase_ai-4.3.0-cp39-abi3-win_amd64.whl
Upload date: Aug 16, 2026
Size: 7.6 MB
Tags: CPython 3.9+, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for briefcase_ai-4.3.0-cp39-abi3-win_amd64.whl
Algorithm	Hash digest
SHA256	`ac1a9556f6642ebca6a0bfbfdbf90b6efe7b5b11c0999f0b1cfe6456ebbc8c78`
MD5	`216a328c74c25d0314bf43cba6bff6cf`
BLAKE2b-256	`c7cf22142f0cf016f7f23e627a3296a68019b20dd460c04b8b9e7afaaf3cf354`

See more details on using hashes here.

Provenance

The following attestation bundles were made for briefcase_ai-4.3.0-cp39-abi3-win_amd64.whl:

Publisher: publish.yml on briefcasebrain/briefcase-ai-sdk

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: briefcase_ai-4.3.0-cp39-abi3-win_amd64.whl
- Subject digest: ac1a9556f6642ebca6a0bfbfdbf90b6efe7b5b11c0999f0b1cfe6456ebbc8c78
- Sigstore transparency entry: 2492980751
- Sigstore integration time: Aug 16, 2026
Source repository:
- Permalink: briefcasebrain/briefcase-ai-sdk@858b1320f683b2ab4bcfe7f1664df293457e0518
- Branch / Tag: refs/heads/main
- Owner: https://github.com/briefcasebrain
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@858b1320f683b2ab4bcfe7f1664df293457e0518
- Trigger Event: workflow_dispatch

File details

Details for the file briefcase_ai-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: briefcase_ai-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Aug 16, 2026
Size: 8.3 MB
Tags: CPython 3.9+, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for briefcase_ai-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`052b5a72077f30791ddcfaec68170d7022b17d688250ceb1adc503dde5b0c7bc`
MD5	`35f62e1943c8f83ae119a789dcae4f04`
BLAKE2b-256	`09ca39a6505f0010ff2ffa4448f18fe82a037c9ced8a0bec4a2ef62dc239633e`

See more details on using hashes here.

Provenance

The following attestation bundles were made for briefcase_ai-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish.yml on briefcasebrain/briefcase-ai-sdk

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: briefcase_ai-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 052b5a72077f30791ddcfaec68170d7022b17d688250ceb1adc503dde5b0c7bc
- Sigstore transparency entry: 2492980993
- Sigstore integration time: Aug 16, 2026
Source repository:
- Permalink: briefcasebrain/briefcase-ai-sdk@858b1320f683b2ab4bcfe7f1664df293457e0518
- Branch / Tag: refs/heads/main
- Owner: https://github.com/briefcasebrain
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@858b1320f683b2ab4bcfe7f1664df293457e0518
- Trigger Event: workflow_dispatch

File details

Details for the file briefcase_ai-4.3.0-cp39-abi3-macosx_11_0_arm64.whl.

File metadata

Download URL: briefcase_ai-4.3.0-cp39-abi3-macosx_11_0_arm64.whl
Upload date: Aug 16, 2026
Size: 7.9 MB
Tags: CPython 3.9+, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for briefcase_ai-4.3.0-cp39-abi3-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`7bd4bccdaa5f0b8546b47dd7f78484b1fbb453ef46b0766f4bec4b24ea2a109c`
MD5	`8cdd6991dd9b6e79eb89a0b8c591adf9`
BLAKE2b-256	`44fcb032b928209eb543db6093a92968b6b42f18f26a91b9f9b0af0a6cb5568c`

See more details on using hashes here.

Provenance

The following attestation bundles were made for briefcase_ai-4.3.0-cp39-abi3-macosx_11_0_arm64.whl:

Publisher: publish.yml on briefcasebrain/briefcase-ai-sdk

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: briefcase_ai-4.3.0-cp39-abi3-macosx_11_0_arm64.whl
- Subject digest: 7bd4bccdaa5f0b8546b47dd7f78484b1fbb453ef46b0766f4bec4b24ea2a109c
- Sigstore transparency entry: 2492980904
- Sigstore integration time: Aug 16, 2026
Source repository:
- Permalink: briefcasebrain/briefcase-ai-sdk@858b1320f683b2ab4bcfe7f1664df293457e0518
- Branch / Tag: refs/heads/main
- Owner: https://github.com/briefcasebrain
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@858b1320f683b2ab4bcfe7f1664df293457e0518
- Trigger Event: workflow_dispatch

File details

Details for the file briefcase_ai-4.3.0-cp39-abi3-macosx_10_12_x86_64.whl.

File metadata

Download URL: briefcase_ai-4.3.0-cp39-abi3-macosx_10_12_x86_64.whl
Upload date: Aug 16, 2026
Size: 8.0 MB
Tags: CPython 3.9+, macOS 10.12+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for briefcase_ai-4.3.0-cp39-abi3-macosx_10_12_x86_64.whl
Algorithm	Hash digest
SHA256	`eacc9a4e0b0849368396d018b8deb1e4667e46ed94c5533fc61f9a7535df0c04`
MD5	`35ebd92e0629a458a736f87d3e012477`
BLAKE2b-256	`d1c4124eb136a6eb52524d65cfe00009f351ab1e451c63b5e25d255f28974d5c`

See more details on using hashes here.

Provenance

The following attestation bundles were made for briefcase_ai-4.3.0-cp39-abi3-macosx_10_12_x86_64.whl:

Publisher: publish.yml on briefcasebrain/briefcase-ai-sdk

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: briefcase_ai-4.3.0-cp39-abi3-macosx_10_12_x86_64.whl
- Subject digest: eacc9a4e0b0849368396d018b8deb1e4667e46ed94c5533fc61f9a7535df0c04
- Sigstore transparency entry: 2492980637
- Sigstore integration time: Aug 16, 2026
Source repository:
- Permalink: briefcasebrain/briefcase-ai-sdk@858b1320f683b2ab4bcfe7f1664df293457e0518
- Branch / Tag: refs/heads/main
- Owner: https://github.com/briefcasebrain
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@858b1320f683b2ab4bcfe7f1664df293457e0518
- Trigger Event: workflow_dispatch

Release history Release notifications | RSS feed

4.4.0

Aug 16, 2026

This release

4.3.0

Aug 16, 2026

4.2.0

Aug 16, 2026

4.1.0

Aug 14, 2026

4.0.1

Aug 12, 2026

4.0.0

Aug 12, 2026

3.3.0

Jun 5, 2026

3.2.2

Jun 3, 2026

3.2.1

May 30, 2026

3.2.0

May 30, 2026

3.0.0

Mar 22, 2026

2.5.3 yanked

Mar 13, 2026

2.5.2 yanked

Mar 12, 2026

2.5.1 yanked

Mar 9, 2026

2.5.0 yanked

Mar 9, 2026

2.4.2 yanked

Mar 2, 2026

2.4.1

Apr 7, 2026

2.4.0 yanked

Mar 1, 2026

2.3.0 yanked

Feb 26, 2026

2.2.3 yanked

Feb 26, 2026

2.2.1 yanked

Feb 26, 2026

2.2.0 yanked

Feb 26, 2026

2.1.30 yanked

Feb 23, 2026

2.1.29 yanked

Feb 23, 2026

2.1.28 yanked

Feb 23, 2026

2.1.27 yanked

Feb 23, 2026

2.1.26 yanked

Feb 23, 2026

2.1.25 yanked

Feb 22, 2026

2.1.24 yanked

Feb 19, 2026

2.1.23 yanked

Feb 8, 2026

2.1.19 yanked

Feb 3, 2026

2.1.18 yanked

Feb 3, 2026

2.1.13 yanked

Feb 3, 2026

2.1.2 yanked

Jan 28, 2026

2.1.1 yanked

Jan 28, 2026

2.1.0 yanked

Jan 28, 2026

2.0.9 yanked

Jan 28, 2026

2.0.8 yanked

Jan 28, 2026

0.1.0 yanked

Dec 23, 2025

briefcase-ai 4.3.0

Briefcase AI SDK

Install

Quick Example

Evaluations and RL

Logging

Using with AI tools (Cursor, Claude Code, Codex, …)

Extras

Managed platform

Telemetry

Links

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License expression

Requires

Provides Extra

Tags

Classifiers

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

Release history Release notifications | RSS feed