Skip to content
ai-supply.store
DécouvrirCatégoriesClassementsCommunautéAgent APIFAQ
Se connecterInscription gratuite
catalog / Orchestration / Headroom
◇MCP serverOrchestrationFree

Headroom

Compress tool outputs, logs, files and RAG chunks before they reach the LLM — 60-95% fewer tokens, same answers.

@ai-supply
Installations38k
⟳ upstream v0.33.0 · updated 8d ago
↗ Dépôt source
← More OrchestrationOrchestration leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals69capabilities surfaced1known CVE5of 20 OWASP controls clear
Low-confidence secret matchSuspicious network referencesBroad capability surfaceSuspicious network references
scanned 5d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Headroom

Compress tool outputs, logs, files and RAG chunks before they reach the LLM — 60–95% fewer tokens with the same answers. Available as a library, a proxy, and an MCP server, so it drops into the agent context pipeline.

Highlights:

  • MCP tools headroom_compress / headroom_retrieve
  • AST-aware code compressors (Python, JS, Go, Rust, Java, C++)
  • Cross-agent memory (Claude, Codex, Gemini) with auto-dedup
  • headroom learn mines failed sessions and writes corrections

Install

As an MCP server (works with Claude, Codex, Cursor, Aider, Copilot). See the repo for the exact config; typical Python install:

pip install headroom

Then register the MCP server in your client, or run the proxy / use the library directly.

  • Repo: https://github.com/chopratejas/headroom
  • License: Apache-2.0
Rating rank
#1
of 16 in Orchestration
Install rank
#12
of 16 in Orchestration
Security score
88/100 · B
review
Security rank
#7
of 16 in Orchestration
Installs
38k
cat avg 126k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Orchestration leaderboard →
! Security: Review · 8888/100 · grade Bscanned 5d ago
✓ no compromise signals70 risk-surface · 10/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secretsinstall: postinstall
egress → headroom-docs.vercel.app, download.pytorch.org, pypi.org, registry.npmjs.org, npm.pkg.github.com, docs.python.org, oraios.github.io, keepachangelog.com +21

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM05Improper Output Handlingcritical
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — pipe-to-shell install · headroomlabs-ai-headroom-6d5516d/.github/workflows/ci.yml (CWE-494)expected
•Suspicious code patterns — dynamic code execution · headroomlabs-ai-headroom-6d5516d/.github/workflows/eval.yml (CWE-95)expected
•Suspicious code patterns — destructive rm -rf / · headroomlabs-ai-headroom-6d5516d/Dockerfile (CWE-78)expected
•Suspicious code patterns — OS command execution; dynamic os import · headroomlabs-ai-headroom-6d5516d/benchmarks/cache_bust_trace_report.py (CWE-78)expected
•Suspicious code patterns — OS command execution · headroomlabs-ai-headroom-6d5516d/benchmarks/cache_validation_bundle.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · headroomlabs-ai-headroom-6d5516d/e2e/wrap/Dockerfile (CWE-78)expected
•Suspicious code patterns — OS command execution; environment/secret exfiltration · headroomlabs-ai-headroom-6d5516d/e2e/wrap/run.py (CWE-78)expected
•Suspicious code patterns — environment/secret exfiltration · headroomlabs-ai-headroom-6d5516d/headroom/copilot_auth.py (CWE-200)expected
•Suspicious code patterns — OS command execution; dynamic code execution · headroomlabs-ai-headroom-6d5516d/headroom/evals/suite_runner.py (CWE-78)expected
•Suspicious code patterns — child_process exec · headroomlabs-ai-headroom-6d5516d/headroom/providers/opencode/_dist/entry.opencode.js (CWE-78)expected
•Suspicious code patterns — bash reverse shell (/dev/tcp) · headroomlabs-ai-headroom-6d5516d/scripts/install.sh (CWE-78)expected
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/tests/integration_cache_drift.rs (CWE-77)expected
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Low-confidence secret match — possible: JWT · headroomlabs-ai-headroom-6d5516d/.gitguardian.yaml (CWE-798)risk surface
•Embedded credentials — found: AWS access key id · headroomlabs-ai-headroom-6d5516d/crates/headroom-core/tests/auth_mode.rs (CWE-798)expected
•Low-confidence secret match — possible: JWT, hardcoded credential (test/sample) · headroomlabs-ai-headroom-6d5516d/tests/test_cache_aligner_detector_only.py (CWE-798)risk surface
•Low-confidence secret match — 1 possible: jwt · headroomlabs-ai-headroom-6d5516d/crates/headroom-core/benches/auth_mode.rs (CWE-798)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · headroomlabs-ai-headroom-6d5516d/headroom/config.py (CWE-798)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · headroomlabs-ai-headroom-6d5516d/headroom/cli/proxy.py (CWE-798)risk surface
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 27 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/docs/package.jsonrisk surface
•npm install-lifecycle script — postinstall run on install — executes arbitrary code · headroomlabs-ai-headroom-6d5516d/docs/package.json (CWE-506)risk surface
•Dependency manifest — 5 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/plugins/openclaw/package.jsonrisk surface
•Dependency manifest — 6 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/plugins/opencode/package.jsonrisk surface
•Dependency manifest — 10 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/sdk/typescript/package.jsonrisk surface
•Vulnerable dependencies — 83 known vulnerabilities in: crossbeam-epoch@0.9.18, number_prefix@0.4.0, paste@1.0.15, agno@2.4.5, anyhow@1.0.102, brace-expansion@5.0.6, click@8.3.1, gitpython@3.1.50 (CWE-1395)known CVE · -12 pts
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · headroomlabs-ai-headroom-6d5516d/.actrcexpected
•External endpoints declared — 2 distinct host(s) · headroomlabs-ai-headroom-6d5516d/.github/ISSUE_TEMPLATE/config.ymlexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · headroomlabs-ai-headroom-6d5516d/.github/workflows/ci.yml (CWE-272)risk surface
•Egress to a private/loopback host — 127.0.0.1 · headroomlabs-ai-headroom-6d5516d/.github/workflows/ci.yml (CWE-918)expected
•External endpoints declared — 4 distinct host(s) · headroomlabs-ai-headroom-6d5516d/.github/workflows/ci.ymlexpected
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · headroomlabs-ai-headroom-6d5516d/.github/workflows/release.yml (CWE-272)risk surface
•External endpoints declared — 3 distinct host(s) · headroomlabs-ai-headroom-6d5516d/.serena/project.ymlexpected
•External endpoints declared — 5 distinct host(s) · headroomlabs-ai-headroom-6d5516d/CHANGELOG.mdexpected
•External endpoints declared — 16 distinct host(s) · headroomlabs-ai-headroom-6d5516d/README.mdexpected
•External endpoints declared — 6 distinct host(s) · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/src/bedrock/invoke.rsexpected
•External endpoints declared — 8 distinct host(s) · headroomlabs-ai-headroom-6d5516d/docs/content/docs/proxy.mdxexpected
•Egress to a private/loopback host — 0.0.0.127 · headroomlabs-ai-headroom-6d5516d/headroom/cli/init.py (CWE-918)expected
•Egress to a private/loopback host — 0.0.0.127, 127.0.0.1 · headroomlabs-ai-headroom-6d5516d/headroom/cli/wrap.py (CWE-918)expected
•External endpoints declared — 18 distinct host(s) · headroomlabs-ai-headroom-6d5516d/headroom/cli/wrap.pyexpected
•Egress to a private/loopback host — 127.0.0.1, [::1] · headroomlabs-ai-headroom-6d5516d/plugins/headroom-oauth2/tests/test_oauth2.py (CWE-918)expected
•External endpoints declared — 13 distinct host(s) · headroomlabs-ai-headroom-6d5516d/plugins/opencode/src/transport.test.tsexpected
•External endpoints declared — 66 distinct host(s) · headroomlabs-ai-headroom-6d5516d/sbom/headroom-python-licenses.csvexpected
•External endpoints declared — 7 distinct host(s) · headroomlabs-ai-headroom-6d5516d/sdk/typescript/package-lock.jsonexpected
•External endpoints declared — 11 distinct host(s) · headroomlabs-ai-headroom-6d5516d/tests/test_banner_upstream_targets.pyexpected
•External endpoints declared — 9 distinct host(s) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_wrap_codex.pyexpected
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Low-confidence secret match — possible: JWT · headroomlabs-ai-headroom-6d5516d/.gitguardian.yaml (CWE-798)risk surface
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · headroomlabs-ai-headroom-6d5516d/benchmarks/comprehensive_eval.py (CWE-200)risk surface
•Embedded credentials — found: AWS access key id · headroomlabs-ai-headroom-6d5516d/crates/headroom-core/tests/auth_mode.rs (CWE-798)expected
•Low-confidence secret match — possible: JWT, hardcoded credential (test/sample) · headroomlabs-ai-headroom-6d5516d/tests/test_cache_aligner_detector_only.py (CWE-798)risk surface
•Low-confidence secret match — 1 possible: jwt · headroomlabs-ai-headroom-6d5516d/crates/headroom-core/benches/auth_mode.rs (CWE-798)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · headroomlabs-ai-headroom-6d5516d/headroom/config.py (CWE-798)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · headroomlabs-ai-headroom-6d5516d/headroom/cli/proxy.py (CWE-798)risk surface
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · headroomlabs-ai-headroom-6d5516d/headroom/cli/wrap.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML09Output Integritycritical
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — pipe-to-shell install · headroomlabs-ai-headroom-6d5516d/.github/workflows/ci.yml (CWE-494)expected
•Suspicious code patterns — dynamic code execution · headroomlabs-ai-headroom-6d5516d/.github/workflows/eval.yml (CWE-95)expected
•Suspicious code patterns — destructive rm -rf / · headroomlabs-ai-headroom-6d5516d/Dockerfile (CWE-78)expected
•Suspicious code patterns — OS command execution; dynamic os import · headroomlabs-ai-headroom-6d5516d/benchmarks/cache_bust_trace_report.py (CWE-78)expected
•Suspicious code patterns — OS command execution · headroomlabs-ai-headroom-6d5516d/benchmarks/cache_validation_bundle.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · headroomlabs-ai-headroom-6d5516d/e2e/wrap/Dockerfile (CWE-78)expected
•Suspicious code patterns — OS command execution; environment/secret exfiltration · headroomlabs-ai-headroom-6d5516d/e2e/wrap/run.py (CWE-78)expected
•Suspicious code patterns — environment/secret exfiltration · headroomlabs-ai-headroom-6d5516d/headroom/copilot_auth.py (CWE-200)expected
•Suspicious code patterns — OS command execution; dynamic code execution · headroomlabs-ai-headroom-6d5516d/headroom/evals/suite_runner.py (CWE-78)expected
•Suspicious code patterns — child_process exec · headroomlabs-ai-headroom-6d5516d/headroom/providers/opencode/_dist/entry.opencode.js (CWE-78)expected
•Suspicious code patterns — bash reverse shell (/dev/tcp) · headroomlabs-ai-headroom-6d5516d/scripts/install.sh (CWE-78)expected
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/tests/integration_cache_drift.rs (CWE-77)expected
⚠ML06AI Supply Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 27 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/docs/package.jsonrisk surface
•npm install-lifecycle script — postinstall run on install — executes arbitrary code · headroomlabs-ai-headroom-6d5516d/docs/package.json (CWE-506)risk surface
•Dependency manifest — 5 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/plugins/openclaw/package.jsonrisk surface
•Dependency manifest — 6 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/plugins/opencode/package.jsonrisk surface
•Dependency manifest — 10 npm dependencies declared · headroomlabs-ai-headroom-6d5516d/sdk/typescript/package.jsonrisk surface
•Vulnerable dependencies — 83 known vulnerabilities in: crossbeam-epoch@0.9.18, number_prefix@0.4.0, paste@1.0.15, agno@2.4.5, anyhow@1.0.102, brace-expansion@5.0.6, click@8.3.1, gitpython@3.1.50 (CWE-1395)known CVE · -12 pts
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (45) · hygiene / uncategorized
•Unrecognized file type — '.actrc' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.actrcrisk surface
•Unrecognized file type — '.example' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.actrc.local.examplerisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.codegraph/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.devcontainer/Dockerfilerisk surface
•Unrecognized file type — '.dockerignore' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.dockerignorerisk surface
•Unrecognized file type — '.git-blame-ignore-revs' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.git-blame-ignore-revsrisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.gitattributesrisk surface
•Suspicious network references — raw IP URL (12 URLs) · headroomlabs-ai-headroom-6d5516d/.github/workflows/ci.ymlrisk surface
•Suspicious network references — raw IP URL (1 URLs) · headroomlabs-ai-headroom-6d5516d/.github/workflows/network-diff-capture.ymlrisk surface
•Unrecognized file type — '.releasemetadata' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/.releasemetadatarisk surface
•Suspicious network references — raw IP URL (3 URLs) · headroomlabs-ai-headroom-6d5516d/Dockerfilerisk surface
•Suspicious network references — raw IP URL (8 URLs) · headroomlabs-ai-headroom-6d5516d/RUST_DEV.mdrisk surface
•Suspicious network references — raw IP URL (10 URLs) · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/src/bedrock/invoke.rsrisk surface
•Suspicious network references — raw IP URL (7 URLs) · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/src/config.rsrisk surface
•Suspicious network references — raw IP URL (2 URLs) · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/tests/common/mod.rsrisk surface
•Suspicious network references — raw IP URL (9 URLs) · headroomlabs-ai-headroom-6d5516d/crates/headroom-proxy/tests/integration_metrics.rsrisk surface
•Unrecognized file type — '.c' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/crates/headroom-py/glibc_compat.crisk surface
•Unrecognized file type — '.hcl' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/docker-bake.hclrisk surface
•Unrecognized file type — '.runner' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/docker/differential-network-capture/Dockerfile.runnerrisk surface
•Unrecognized file type — '.mdx' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/docs/content/docs/agent-orchestration.mdxrisk surface
•Suspicious network references — raw IP URL (5 URLs) · headroomlabs-ai-headroom-6d5516d/docs/content/docs/claude-code-azure-foundry.mdxrisk surface
•Suspicious network references — raw IP URL (6 URLs) · headroomlabs-ai-headroom-6d5516d/docs/content/docs/opencode.mdxrisk surface
•Suspicious network references — raw IP URL (17 URLs) · headroomlabs-ai-headroom-6d5516d/docs/content/docs/proxy.mdxrisk surface
•Unrecognized file type — '.mjs' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/docs/next.config.mjsrisk surface
•Unrecognized file type — '.gitkeep' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/docs/overrides/.gitkeeprisk surface
•Disallowed file type — '.ps1' executables are not permitted · headroomlabs-ai-headroom-6d5516d/e2e/_lib/make_shim.ps1 (CWE-434)risk surface
•Suspicious network references — raw IP URL (4 URLs) · headroomlabs-ai-headroom-6d5516d/e2e/docker-native-install.shrisk surface
•Unrecognized file type — '.template' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/examples/deployment/macos-launchagent/com.headroom.proxy.plist.templaterisk surface
•Suspicious network references — raw IP URL (41 URLs) · headroomlabs-ai-headroom-6d5516d/headroom/cli/wrap.pyrisk surface
•Suspicious network references — suspicious TLD (11 URLs) · headroomlabs-ai-headroom-6d5516d/headroom/providers/openai_compatible.pyrisk surface
•Suspicious network references — suspicious TLD (17 URLs) · headroomlabs-ai-headroom-6d5516d/headroom/tools.jsonrisk surface
•Suspicious network references — raw IP URL (31 URLs) · headroomlabs-ai-headroom-6d5516d/llms.txtrisk surface
•Suspicious network references — raw IP URL (15 URLs) · headroomlabs-ai-headroom-6d5516d/plugins/headroom-oauth2/tests/test_oauth2.pyrisk surface
•Unrecognized file type — '.npmignore' is not on the allowlist · headroomlabs-ai-headroom-6d5516d/plugins/openclaw/.npmignorerisk surface
•Suspicious network references — raw IP URL (43 URLs) · headroomlabs-ai-headroom-6d5516d/plugins/openclaw/test/gateway-config.test.tsrisk surface
•Suspicious network references — raw IP URL (26 URLs) · headroomlabs-ai-headroom-6d5516d/plugins/openclaw/test/plugin-runtime-routing.test.tsrisk surface
•Suspicious network references — raw IP URL (40 URLs) · headroomlabs-ai-headroom-6d5516d/plugins/openclaw/test/proxy-manager.test.tsrisk surface
•Suspicious network references — raw IP URL, suspicious TLD (43 URLs) · headroomlabs-ai-headroom-6d5516d/plugins/opencode/src/transport.test.tsrisk surface
•Suspicious network references — suspicious TLD (8 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_binaries.pyrisk surface
•Suspicious network references — raw IP URL (13 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_init_cli.pyrisk surface
•Suspicious network references — raw IP URL (32 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_install_cli.pyrisk surface
•Suspicious network references — raw IP URL (35 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_wrap_claude_base_url.pyrisk surface
•Suspicious network references — raw IP URL (24 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_wrap_claude_vertex_proxy_env.pyrisk surface
•Suspicious network references — raw IP URL (62 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_wrap_codex.pyrisk surface
•Suspicious network references — raw IP URL (18 URLs) · headroomlabs-ai-headroom-6d5516d/tests/test_cli/test_wrap_copilot.pyrisk surface
✔ verified source · pinned headroomlabs-ai-headroom-6d5516d
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/headroom/check). Click a policy:

Consume Headroom programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/headroom

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/headroom/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add headroom

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/headroom/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "headroom" })
OpenAPI spec →
vlatest
! Security: Review · 881mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Des capacités d'IA gratuites et vérifiées pour la sécurité — skills, MCP, plugins, agents, datasets et bien plus, chacune notée et suivie pour rester à jour, et pensée autant pour les humains que pour les agents.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalogue
  • Découvrir
  • Catégories
  • Classements
  • Benchmarks
  • Sécurité
  • Scan a repo
Communauté
  • Communauté
  • FAQ
Pour les agents
  • Démarrage rapide (60s)
  • Autoriser un agent
  • Agent API
  • Spécification OpenAPI
Pour les développeurs
  • Publier
  • Tableau de bord
Compte
  • Créer un compte
  • Se connecter
  • Paramètres
Mentions légales
  • Conditions
  • Accord éditeur
  • Utilisation acceptable
  • Confidentialité