Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-10-19 12:05 UTC

pipecat-ai / pipecat-context-hub

Local-first MCP server providing Pipecat docs, examples, and API context for AI coding agents

PythonBSD-2-Clause★ 8 stars⑂ 2 forkssince Feb 2026View on GitHub ↗
KindCommand-line toolMCP serverPluginLibraryhow this is determined
#ai-coding#developer-tools#mcp#pipecat#retreival#retrieval

pipecat-ai/pipecat-context-hub holds a health index of 87 out of 100, placing it in the Excellent band. It scores highest on Vitality (90/100) and lowest on Community & Adoption (51/100). It was last updated today. A single contributor accounts for most of its recent work.

87
overall / 100
Excellent

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

87
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

Score profile

Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.

The weighted overall 73 is calibrated to 87 on the published index scale (record calibration 2026-08-02).

Ownership

PipecatOrganization
780 followers66 public repossince May 2024

This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIpipecat-ai-context-hub0.9.120,458150 days agoclaude-codecursormcpmodel-context-protocolpipecatragvoice-ai

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

90Excellent · 21% of overall

Development activity

83Excellent
How it's scored
36/36Push recency — last push 0 days ago
19.4/36Commit cadence — 28/52 weeks with commits
18/18Commit volume — 1,331 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 10 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year1,331
human_commit_share1
days_since_last_push0
active_weeks_last_year28

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 37 releases published
36/36Release recency — latest release 0 days ago
27/27Release cadence — a release every ~8.5 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count37
latest_release_tagv0.9.1
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases8.5
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

51Moderate · 17% of overall

Popularity & adoption

14Critical
How it's scored
13.7/60Stars — 8 stars
0/25Forks — 2 forks
0/15Watchers — 0 watchers
Inputs used
forks2
stars8
watchers0
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

77Good
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (BSD-2-Clause)
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges—
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_services—
has_pull_request_templateyes

Ecosystem adoption (downloads)

72Good
How it's scored
57.5/80Monthly downloads — 20,458 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagespipecat-ai-context-hub
dependents—
ecosystemspypi
total_downloads—
monthly_downloads20,458
unverified_packages_excluded—
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

63Moderate · 23% of overall

Maintainer resilience (bus factor)

24At Risk
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0.9/22.5Commit distribution — top contributor authored 96% of commits
4.1/13.5Contributor breadth — 3 contributors
10/10OpenSSF Scorecard: Contributors — project has 3 contributing companies or organizations -- score normalized to 10
Inputs used
bus_factor1
contributors_sampled3
top_contributor_share0.96

Issue & PR responsiveness

73Good
How it's scored
34.4/42Issue resolution — 82% of issues closed
28/30PR acceptance — 139/149 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
1.5/15OpenSSF Scorecard: Code-Review — Found 1/6 approved changesets -- score normalized to 1
Inputs used
merged_prs139
open_issues2
closed_issues9
prs_merged_7d17
prs_decided_7d18
prs_merged_30d18
prs_decided_30d19
issue_closed_ratio0.818
closed_unmerged_prs10
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

69Good
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
20.8/25Owner reach — 780 followers of pipecat-ai
17.9/25Track record — 66 public repos, account ~2 yr old
Inputs used
followers780
owner_typeOrganization
is_verifiedno
owner_loginpipecat-ai
public_repos66
account_age_days889

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 0 days ago
20/20Version history — 15 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagespipecat-ai-context-hub
ecosystemspypi
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

86Excellent · 19% of overall

Engineering practices

84Excellent
How it's scored
24/24CI workflows — 5 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff])
0/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 6 out of 6 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://docs.pipecat.ai/api-reference/context-hub
10/10Repository description
10/10Topics — 6 topics
0/10Wiki
Inputs used
topicsai-coding, developer-tools, mcp, pipecat, retreival, retrieval
has_wikino
homepage—
docs_sitehttps://docs.pipecat.ai/api-reference/context-hub
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

69Good · 16% of overall

Security posture

73Good
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — no data
2.5/2.5CI-Tests — 6 out of 6 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0.8/7.5Code-Review — Found 1/6 approved changesets -- score normalized to 1
2.5/2.5Contributors — project has 3 contributing companies or organizations -- score normalized to 10
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 10 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — no data
2/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 4
5/5SAST — SAST tool is run on all commits
2/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
7.5/7.5Token-Permissions — GitHub workflow tokens follow principle of least privilege
4.5/7.5Vulnerabilities — 4 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated15
scorecard_versionv5.5.0
checks_inconclusive3
scorecard_aggregate7.3
Excluded from scoring (no data or not applicable): Branch-Protection, Packaging, Signed-Releases. Remaining weights renormalized.

Dependency advisories

52Moderate
How it's scored
7/35Direct dependencies free of known advisories — 1 affected: chromadb 1.5.9 (critical 10.0)
0/25Indirect dependencies free of known advisories — transitive set not separable from development and test dependencies in this scope
32/40No advisories left outstanding — 1 advisory-carrying package(s) unaddressed past 90 days; oldest published 153 days ago
Inputs used
sourceosv
advisories8
affected_packages1
assessed_packages148
unassessed_packages0
affected_by_severitycritical 1
direct_affected_packages1
Excluded from scoring (no data or not applicable): Indirect dependencies free of known advisories. Remaining weights renormalized. Matched 148 resolved dependencies against OSV. This repository publishes no package the index resolves, so the repository dependency graph was assessed instead. That graph mixes development and test pins with shipped dependencies, so only the declared runtime dependencies are scored; transitive findings are reported as context and excluded from the score. Reachability is not analyzed.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

83Excellent · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 95 of 100 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share0.95
agent_instruction_filesAGENTS.md, CLAUDE.md
agent_instruction_max_bytes38,185

Verify loop (build / test / typecheck)

76Good
How it's scored
18/18One-command bootstrap — justfile
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff])
11/11Static type checking — src/pipecat_context_hub/py.typed
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
0/8Automated maintenance — no automated dependency updates observed
4/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 4
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_filesjustfile
has_devcontainerno
has_linter_configyes
typecheck_configssrc/pipecat_context_hub/py.typed
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0

Code legibility for models

78Good
How it's scored
27/45Type-checkable code — Python with type-check config (src/pipecat_context_hub/py.typed)
51.3/55Manageable file sizes — 12/178 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes328,766
source_files_sampled178
oversized_source_files12

Machine-readable interfaces

100Exceptional
How it's scored
0/40API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
20/20MCP server
40/40Runnable examples — examples
Inputs used
example_dirsexamples
has_mcp_signalyes
api_schema_files—
interfaces_expected_of—
Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto). Remaining weights renormalized.

Key facts

8GitHub stars
3contributors
1,331commits, last 12 months
0days since last push
37releases
1bus factor
2open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • deps.dev does not index pypi:pipecat-ai-context-hub@0.9.1; advisories assessed against the repository dependency graph instead

More detail

Star and fork history 0 ★ / 2 ⇿
0Stars
2Forks
23Releases

When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.

111222212026-032026-062026-09
Major 0Minor 7Patch 16
OpenSSF Scorecard 7.3 / 10
7.3aggregate

Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-10-19 12:04 UTC

10Binary-Artifactsno binaries found in the repo
n/aBranch-Protectioninternal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md
10CI-Tests6 out of 6 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
1Code-ReviewFound 1/6 approved changesets -- score normalized to 1
10Contributorsproject has 3 contributing companies or organizations -- score normalized to 10
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 10 issue activity found in the last 90 days -- score normalized to 10
n/aPackagingpackaging workflow not detected
4Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 4
10SASTSAST tool is run on all commits
4Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
10Token-PermissionsGitHub workflow tokens follow principle of least privilege
6Vulnerabilities4 existing vulnerabilities detected
Direct dependencies 15
RegistryPackageVersion constraintManifest
PyPIpydantic>=2.0,<3.0pyproject.toml
PyPImcp>=2.0,<3.0pyproject.toml
PyPIhttpx>=0.27,<1.0pyproject.toml
PyPIchromadb>=1.5,<1.6pyproject.toml
PyPIonnxruntime>=1.17,<2.0pyproject.toml
PyPItokenizers>=0.15,<1.0pyproject.toml
PyPIhuggingface-hub>=0.20,<2.0pyproject.toml
PyPInumpy>=1.24,<3.0pyproject.toml
PyPIgitpython>=3.1.59,<4.0pyproject.toml
PyPIclick>=8.0,<9.0pyproject.toml
PyPItree-sitter>=0.25,<1.0pyproject.toml
PyPItree-sitter-typescript>=0.23,<1.0pyproject.toml
PyPIpackaging>=21.0,<27.0pyproject.toml
PyPIcryptography>=50.0.0pyproject.toml
PyPItomlkit>=0.15.2,<1.0pyproject.toml
All dependencies 148

Full resolved dependency set from the GitHub dependency graph: 15 direct and 133 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIchromadb1.5.9direct
PyPIclick8.4.2direct
PyPIcryptography50.0.0direct
PyPIgitpython3.1.62direct
PyPIhttpx0.28.1direct
PyPIhuggingface-hub1.9.2direct
PyPImcp2.2.0direct
PyPInumpy2.4.2direct
PyPIonnxruntime1.24.1direct
PyPIpackaging24.2direct
PyPIpydantic2.12.5direct
PyPItokenizers0.22.2direct
PyPItomlkit0.15.2direct
PyPItree-sitter0.25.2direct
PyPItree-sitter-typescript0.23.2direct
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIanyio4.14.2indirect
PyPIarrow1.4.0indirect
PyPIattrs25.4.0indirect
PyPIbandit1.9.4indirect
PyPIbcrypt5.0.0indirect
PyPIboolean-py5.0indirect
PyPIbuild1.4.0indirect
PyPIcachecontrol0.14.4indirect
PyPIcertifi2026.1.4indirect
PyPIcffi2.0.0indirect
PyPIchardet5.2.0indirect
PyPIcharset-normalizer3.4.4indirect
PyPIcolorama0.4.6indirect
PyPIcyclonedx-bom7.3.0indirect
PyPIcyclonedx-python-lib11.7.0indirect
PyPIdefusedxml0.7.1indirect
PyPIdurationpy0.10indirect
PyPIfilelock3.24.2indirect
PyPIflatbuffers25.12.19indirect
PyPIfqdn1.5.1indirect
PyPIfsspec2026.9.0indirect
PyPIgitdb4.0.12indirect
PyPIgoogleapis-common-protos1.72.0indirect
PyPIgrpcio1.78.0indirect
PyPIh110.16.0indirect
PyPIhf-xet1.4.3indirect
PyPIhttpcore1.0.9indirect
PyPIhttpcore22.12.0indirect
PyPIhttptools0.7.1indirect
PyPIhttpx22.12.0indirect
PyPIhttpx2-jsfetch1.0indirect
PyPIidna3.19indirect
PyPIimportlib-metadata8.7.1indirect
PyPIimportlib-resources6.5.2indirect
PyPIiniconfig2.3.0indirect
PyPIisoduration20.11.0indirect
PyPIjoblib1.5.3indirect
PyPIjsonpointer3.1.1indirect
PyPIjsonschema4.26.0indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIkubernetes35.0.0indirect
PyPIlark1.3.1indirect
PyPIlibrt0.8.1indirect
PyPIlicense-expression30.4.4indirect
PyPIllvmlite0.46.0indirect
PyPIlxml6.1.0indirect
PyPImarkdown-it-py4.0.0indirect
PyPImcp-types2.2.0indirect
PyPImdurl0.1.2indirect
PyPImmh35.2.0indirect
PyPImpmath1.3.0indirect
PyPImsgpack1.2.1indirect
PyPImypy1.19.1indirect
PyPImypy-extensions1.1.0indirect
PyPInumba0.64.0indirect
PyPIoauthlib4.0.0indirect
PyPIopentelemetry-api1.39.1indirect
PyPIopentelemetry-exporter-otlp-proto-common1.39.1indirect
PyPIopentelemetry-exporter-otlp-proto-grpc1.39.1indirect
PyPIopentelemetry-proto1.39.1indirect
PyPIopentelemetry-sdk1.39.1indirect
PyPIopentelemetry-semantic-conventions0.60b1indirect
PyPIorjson3.11.7indirect
PyPIoverrides7.7.0indirect
PyPIpackageurl-python0.17.6indirect
PyPIpathspec1.0.4indirect
PyPIpip26.2indirect
PyPIpip-api0.0.34indirect
PyPIpip-audit2.10.0indirect
PyPIpip-requirements-parser32.0.1indirect
PyPIpipecat-ai-context-hub0.9.1indirect
PyPIplatformdirs4.9.4indirect
PyPIpluggy1.6.0indirect
PyPIprotobuf6.33.5indirect
PyPIpy-serializable2.1.0indirect
PyPIpybase641.4.3indirect
PyPIpycparser3.0indirect
PyPIpydantic-core2.41.5indirect
PyPIpydantic-settings2.14.2indirect
PyPIpygments2.20.0indirect
PyPIpyjwt2.15.0indirect
PyPIpynndescent0.6.0indirect
PyPIpyparsing3.3.2indirect
PyPIpypika0.51.1indirect
PyPIpyproject-hooks1.2.0indirect
PyPIpytest9.0.3indirect
PyPIpytest-asyncio1.3.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-dotenv1.2.2indirect
PyPIpython-multipart0.0.32indirect
PyPIpywin32311indirect
PyPIpyyaml6.0.3indirect
PyPIreferencing0.37.0indirect
PyPIrequests2.33.0indirect
PyPIrequests-oauthlib2.0.0indirect
PyPIrfc3339-validator0.1.4indirect
PyPIrfc3986-validator0.1.1indirect
PyPIrfc3987-syntax1.1.0indirect
PyPIrich14.3.2indirect
PyPIrpds-py0.30.0indirect
PyPIruff0.15.1indirect
PyPIscikit-learn1.8.0indirect
PyPIscipy1.17.0indirect
PyPIshellingham1.5.4indirect
PyPIsix1.17.0indirect
PyPIsmmap5.0.2indirect
PyPIsortedcontainers2.4.0indirect
PyPIsse-starlette3.2.0indirect
PyPIstarlette1.3.1indirect
PyPIstevedore5.7.0indirect
PyPIsympy1.14.0indirect
PyPItenacity9.1.4indirect
PyPIthreadpoolctl3.6.0indirect
PyPItomli2.4.1indirect
PyPItomli-w1.2.0indirect
PyPItqdm4.67.3indirect
PyPItruststore0.10.4indirect
PyPItyper0.24.0indirect
PyPItyping-extensions4.15.0indirect
PyPItyping-inspection0.4.2indirect
PyPItzdata2025.3indirect
PyPIumap-learn0.5.11indirect
PyPIuri-template1.3.0indirect
PyPIurllib32.8.0indirect
PyPIuvicorn0.41.0indirect
PyPIuvloop0.22.1indirect
PyPIwatchfiles1.1.1indirect
PyPIwebcolors25.10.0indirect
PyPIwebsocket-client1.9.0indirect
PyPIwebsockets16.0indirect
PyPIzipp3.23.0indirect
Dependency advisories 1

This repository publishes no package the index resolves, so its own dependency graph was assessed — 148 packages, which also include development and test pins that never ship: 1 carry known advisories, of which 1 are direct.

PackageVersionRelationSeverityAdvisoriesFixed in
chromadb1.5.9directcritical8—

An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.

Raw JSON report machine-readable

Feedback

Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.

The message is kept through sign-in.

Related records

Inspected repositories sharing catalogue tags or ecosystems with pipecat-ai/pipecat-context-hub. Read them side by side →

96sickn33/agentic-awesome-skillsAAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,115+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.Exceptional95juspay/neurolinkOne TypeScript interface for 24+ LLM providers — swap providers without rewriting. MCP-native (connect any MCP server), voice (TTS/STT/realtime), RAG, memory, file processors. Production-origin: powers Tara, Yama, and Clairvoyance at Juspay.Exceptional98awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessionsExceptional97Observal/ObservalObserval is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.Exceptional95headroomlabs-ai/headroomCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.Exceptional96mcp-use/mcp-useThe fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.Exceptional

Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.

Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.34.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — PyPI.