Public record
Software health reportschema 0.12.0 · metrics 2.10.0 · 2026-07-17 20:20 UTC

Trampoline-AI / predict-rlm

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

PythonMIT★ 413 stars⑂ 44 forkssince Mar 2026View on GitHub ↗
KindLibraryhow this is determined
#dspy#llm#rlm

Trampoline-AI/predict-rlm holds a health index of 77 out of 100, placing it in the Good band. It scores highest on Vitality (85/100) and lowest on Security (51/100). It was last updated today. A single contributor accounts for most of its recent work.

77
overall / 100
Good

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.

77
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 66 is calibrated to 77 on the published index scale (record calibration 2026-08-02).

Ownership

Trampoline AIOrganization
13 followers4 public repossince Apr 2023

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIpredict-rlm0.7.317,860230 days agoaidspylanguage-modelsreasoningrlmtool-use

Metrics by category

Vitality

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

85Excellent · 21% of overall

Development activity

75Good
How it's scored
36/36Push recency — last push 0 days ago
11.1/36Commit cadence — 16/52 weeks with commits
18/18Commit volume — 341 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 5 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year341
human_commit_share—
days_since_last_push0
active_weeks_last_year16

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 23 releases published
36/36Release recency — latest release 0 days ago
27/27Release cadence — a release every ~5.8 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count23
latest_release_tagv0.8.0-alpha0
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases5.8
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?

58Moderate · 17% of overall

Popularity & adoption

58Moderate
How it's scored
42.4/60Stars — 413 stars
13.6/25Forks — 44 forks
1.7/15Watchers — 3 watchers
Inputs used
forks44
stars413
watchers3
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

50Moderate
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (MIT)
0/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges—
has_contributingno
has_issue_templateno
has_code_of_conductno
readme_badge_services—
has_pull_request_templateno

Ecosystem adoption (downloads)

71Good
How it's scored
56.7/80Monthly downloads — 17,860 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagespredict-rlm
dependents—
ecosystemspypi
total_downloads—
monthly_downloads17,860
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?

57Moderate · 23% of overall

Maintainer resilience (bus factor)

30At Risk
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
5.8/22.5Commit distribution — top contributor authored 74% of commits
5.4/13.5Contributor breadth — 4 contributors
10/10OpenSSF Scorecard: Contributors — project has 3 contributing companies or organizations -- score normalized to 10
Inputs used
bus_factor1
contributors_sampled4
top_contributor_share0.744

Issue & PR responsiveness

49Weak
How it's scored
12.9/42Issue resolution — 31% of issues closed
23.4/30PR acceptance — 32/41 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
6/15OpenSSF Scorecard: Code-Review — Found 5/11 approved changesets -- score normalized to 4
Inputs used
merged_prs32
open_issues9
closed_issues4
prs_merged_7d—
prs_decided_7d—
prs_merged_30d—
prs_decided_30d—
issue_closed_ratio0.308
closed_unmerged_prs9
first_time_authors_30d—
first_time_prs_merged_30d—
first_time_prs_decided_30d—
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

62Moderate
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
8.2/25Owner reach — 13 followers of Trampoline-AI
11.7/25Track record — 4 public repos, account ~3 yr old
Inputs used
followers13
owner_typeOrganization
is_verified—
owner_loginTrampoline-AI
public_repos4
account_age_days1,201
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

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 — 23 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagespredict-rlm
ecosystemspypi
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

77Good · 19% of overall

Engineering practices

68Good
How it's scored
24/24CI workflows — 2 workflow(s)
24/24Tests present
0/16Linter config
0/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 7 out of 7 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configno
has_precommit_configno

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://trampoline.ai
10/10Repository description
10/10Topics — 3 topics
0/10Wiki
Inputs used
topicsdspy, llm, rlm
has_wikino
homepagehttps://trampoline.ai
docs_sitehttps://trampoline.ai
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

51Moderate · 16% of overall

Security posture

51Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0.8/7.5Branch-Protection — branch protection is not maximal on development and all release branches
2.5/2.5CI-Tests — 7 out of 7 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
3/7.5Code-Review — Found 5/11 approved changesets -- score normalized to 4
2.5/2.5Contributors — project has 3 contributing companies or organizations -- score normalized to 10
10/10Dangerous-Workflow — no dangerous workflow patterns detected
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 5 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
1/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 2
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
0/5Security-Policy — security policy file not detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
7.5/7.5Vulnerabilities — 0 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate5.1
Excluded from scoring (no data or not applicable): Signed-Releases. Remaining weights renormalized.

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.

70Good · 4% of overall

Agent context & guidance

75Good
How it's scored
45/45Agent instructions — AGENTS.md
0/15Machine-readable docs (llms.txt)
0/40Legible commit history — no data
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share—
agent_instruction_filesAGENTS.md
agent_instruction_max_bytes8,388
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

Verify loop (build / test / typecheck)

63Moderate
How it's scored
18/18One-command bootstrap — Makefile, examples/appworld/Makefile, examples/spreadbench/Makefile, examples/terminal_bench/Makefile
22/22Automated tests
0/11Lint / format config
0/11Static type checking
10/10Reproducible environment — Dockerfile
0/10Demonstrated agent practice — no data
0/8Automated maintenance — no data
2/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 2
Inputs used
has_nixno
has_testsyes
lockfiles—
has_dockerfileyes
typed_languageno
bootstrap_filesMakefile, examples/appworld/Makefile, examples/spreadbench/Makefile, examples/terminal_bench/Makefile
has_devcontainerno
has_linter_configno
typecheck_configs—
agent_commit_share—
toolchain_manifests—
dependency_bot_commit_share—
Excluded from scoring (no data or not applicable): Demonstrated agent practice, Automated maintenance. Remaining weights renormalized.

Code legibility for models

52Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
52.3/55Manageable file sizes — 12/245 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes196,284
source_files_sampled245
oversized_source_files12

Machine-readable interfaces

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

Key facts

413GitHub stars
4contributors
341commits, last 12 months
0days since last push
23releases
1bus factor
9open issues
PyPIpackage ecosystems

More detail

OpenSSF Scorecard 5.1 / 10
5.1aggregate

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 · 2026-07-17 20:19 UTC

10Binary-Artifactsno binaries found in the repo
1Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests7 out of 7 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
4Code-ReviewFound 5/11 approved changesets -- score normalized to 4
10Contributorsproject has 3 contributing companies or organizations -- score normalized to 10
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 5 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
2Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 2
0SASTSAST tool is not run on all commits -- score normalized to 0
0Security-Policysecurity policy file not detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
10Vulnerabilities0 existing vulnerabilities detected
Direct dependencies 6
RegistryPackageVersion constraintManifest
PyPIdeno>=2pyproject.toml
PyPIdspy>=3.2.1pyproject.toml
PyPInest-asyncio>=1.6.0pyproject.toml
PyPIpygments>=2.0.0pyproject.toml
PyPIpydantic>=2.8.2,<3pyproject.toml
PyPItenacity>=8.2.0pyproject.toml
All dependencies 22

Full resolved dependency set from the GitHub dependency graph: 6 direct and 16 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIdeno—direct
PyPIdspy—direct
PyPInest-asyncio—direct
PyPIpydantic—direct
PyPIpygments—direct
PyPItenacity—direct
PyPIformulas—indirect
PyPIgepa—indirect
PyPIipykernel—indirect
PyPIkaleido—indirect
PyPIlitellm—indirect
PyPIopenai—indirect
PyPIopenpyxl—indirect
PyPIplotly—indirect
PyPIpymupdf—indirect
PyPIpytest—indirect
PyPIpytest-asyncio—indirect
PyPIpytest-cov—indirect
PyPIpytest-testdox—indirect
PyPIruff—indirect
PyPItqdm—indirect
PyPIwebsockets—indirect
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 Trampoline-AI/predict-rlm. Read them side by side →

98langwatch/langwatchThe platform for LLM evaluations and AI agent testingExceptional100deepset-ai/haystackOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.Exceptional99google/adk-pythonAn open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.Exceptional99ag2ai/ag2AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3xExceptional99langchain-ai/langgraphBuild resilient agents.Exceptional98googleapis/mcp-toolboxMCP Toolbox for Databases is an open source MCP server for databases.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 v0.12.0 — full methodology · metrics wiki.

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