Item detail

GenseeAI/gensee-crate

GenseeAI/gensee-crate is a full-stack, long-horizon runtime that RepoRadar is tracking in its Apache-2.0 alpha full-stack runtime safety sidec section, currently rated Silver tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 8.9 out of 10.

Score7.8
Popularity54.0
Riskconditional
TierSilver
Score breakdown
Usefulness7.0
Novelty8.0
Momentum6.0
Maturity6.4
Open-source/build8.4
Evidence7.2
Workflow potential8.9
Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for security and platform teams running AI coding agents (Claude Code, Codex, OpenCode, Hermes, custom harnesses) on a fleet of developer endpoints who need long-horizon runtime safety and audit, not a one-shot pre-tool hook: Gensee Crate is the Apache-2.0 alpha sidecar that watches system events, user requests, tool calls, skills, and memory across requests and sessions; for security teams

Who should use it

Security and platform teams running AI coding agents (Claude Code, Codex, OpenCode, Hermes, custom harnesses) on a fleet of developer endpoints who need long-horizon runtime safety and audit, not a one-shot pre-tool hook: Gensee Crate is the Apache-2.0 alpha sidecar that watches system events, user requests, tool calls, skills, and memory across requests and sessionsSecurity teams that need a configurable policy that can allow / ask / deny (the rule schema is in `docs/policy.md`, the enforcement happens inside the agent chat interface in real time)Platform teams that need a defense-in-depth architecture for coding-agent fleets (the README's defense-in-depth diagram is the high-level overview, the policy.md is the rule layer, the dashboard is the operator surface)Security architects evaluating AI coding-agent governance (the long-horizon framing is the right model — most pre-tool hooks miss the cross-request drift; this sidecar is built to track that)Organizations that want a self-hosted alternative to hosted agent-governance SaaS (Apache-2.0 + local sidecar, no data leaves the host by default)Security teams that need lineage + provenance (the offline event tracking tracks files read and written, commands run, network targets reached, hook intent, alerts, and timeline context — the audit trail a security team needs to reconstruct what an agent did across a session)Enterprise teams evaluating a paid tier (the README links to a contact page for the enterprise tier with company-enforced rules, credential and identity controls, and oversight across a distributed fleet — read the enterprise tier's contract terms before committing)Engineering teams using Claude Code or Codex (the README explicitly lists 'unmodified coding agents such as Claude Code and Codex' as the integration target, so the sidecar slots in without rewriting the agent harness)Security teams adopting a defense-in-depth posture (the README's defense-in-depth diagram is the high-level architecture — policy layer + sidecar enforcement + dashboard + lineage; the alpha status badge is the maturity signal to read first)

Who should skip it

Pass on GenseeAI/gensee-crate if you need something non-technical and turnkey rather than a tool that requires comfort with CLI, dependencies, or system configuration.

About this signal

GenseeAI/gensee-crate is tracked by RepoRadar as a full-stack, long-horizon runtime in the Apache-2.0 alpha full-stack runtime safety sidec section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Silver tier and hard setup difficulty. Across RepoRadar's eight signals, GenseeAI/gensee-crate is strongest on workflow potential (8.9) and open-source/build quality (8.4) and weakest on setup ease (4.2) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned GenseeAI/gensee-crate a composite score of 7.8 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 54.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Risk explanation

**Alpha status: the API and policy schema are still settling.** The README's alpha-status badge is the maturity signal to read first — the sidecar is in alpha, so the API and the policy schema can change between versions. Pin to a specific commit or release tag for any production-pilot evaluation, and budget for a small migration between alpha versions; **macOS-first: Linux and Windows support is on the roadmap, not the first evaluation target.** The macOS-first platform badge scopes the current evaluation target. Fleet deployments on Linux or Windows endpoints will hit the platform-first story — read the roadmap and confirm the timeline before committing to a non-macOS pilot; **Enterprise tier is a paid offering — review the contract terms before committing.** The README links to a contact page for the enterprise tier with company-enforced rules, credential and identity controls, and oversight across a distributed fleet. The Apache-2.0 sidecar is the right starting point for a pilot; the enterprise tier is a separate paid contract. Read the enterprise contract terms (data handling, SLA, support, multi-tenant isolation) before committing any production deployment to the enterprise tier.

Evidence links

Closest alternatives / related signals

genseegensee-crategenseeaigensee-airuntime-safetyagent-safetyagent-governancelong-horizon