Comparison
agentdojo vs stepshield
Verdict
Pick agentdojo if agentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents; pick stepshield if stepShield aids in evaluating temporal guardrail effectiveness on AI agents through step-level annotations, ideal for ensuring security over time.
Markdown twin · agentdojo alternatives · stepshield alternatives
GraphCanon updated Sep 20, 2026
9views this month
vs
Trust & integrity
| Signal | agentdojo | stepshield |
|---|---|---|
| Maintenance | Slowing (94d since push) As of Sep 5, 2026 · github_public_v1 | Active (7d since push) As of Sep 13, 2026 · github_public_v1 |
| Provenance | Not a fork · Organization account As of Sep 5, 2026 · github_public_v1 | Not a fork · Personal account As of Sep 13, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 | Published findings As of Jul 15, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- agentdojo
- A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- stepshield
- Temporal evaluation benchmark for AI agent guardrails
Stars
- agentdojo
- 802
- stepshield
- 76
Forks
- agentdojo
- 205
- stepshield
- 17
Open issues
- agentdojo
- 51
- stepshield
- 18
Language
- agentdojo
- Python
- stepshield
- Python
Adopt for
- agentdojo
- AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
- stepshield
- StepShield aids in evaluating temporal guardrail effectiveness on AI agents through step-level annotations, ideal for ensuring security over time.
Persona
- agentdojo
- -
- stepshield
- -
Runtime
- agentdojo
- -
- stepshield
- -
License
- agentdojo
- MIT
- stepshield
- Other
Last pushed
- agentdojo
- Jun 2, 2026
- stepshield
- Sep 5, 2026
Categories
- agentdojo
- AI Agents, Evaluation & Observability
- stepshield
- AI Agents, Evaluation & Observability
Trust and health
Maintenance
- agentdojo
- Slowing (36%)
- stepshield
- Active (82%)
Days since push
- agentdojo
- 94d
- stepshield
- 7d
Open issues (now)
- agentdojo
- 51
- stepshield
- 18
Stars delta
- agentdojo
- +86 (30d)
- stepshield
- -1 (30d)
Open issues delta
- agentdojo
- +10 (30d)
- stepshield
- +2 (30d)
Owner type
- agentdojo
- Organization
- stepshield
- User
OSV dependency advisories
- agentdojo
- No lockfile (source not queried)
- stepshield
- Published findings
Full report
- agentdojo
- Trust report
- stepshield
- Trust report
Shared compatibility
- Python · agentdojo: Python runtime · stepshield: Python runtime
Choose agentdojo if…
- License: agentdojo is MIT, stepshield is Other.
- Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs..
- Requirements: Min 8 GB RAM.
- Tags unique to agentdojo: large-language-models, prompt-injection, security.
- AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
When NOT to use agentdojo
- Last GitHub push was Jun 2, 2026 (slowing maintenance). Validate activity before betting a new project on agentdojo.
- AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism.
- Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
Choose stepshield if…
- License: stepshield is Other, agentdojo is MIT.
- Tags unique to stepshield: agent-security, ai-safety, dataset, guardrails.
- When you need to measure the timing of interventions rather than just if they occur
When NOT to use stepshield
- If your project does not require temporal analysis of guardrail performance
- When you seek real-time intervention and do not need pre-defined trajectory datasets
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (ethz-spylab/agentdojo) · observed Sep 20, 2026
- GitHub forks (ethz-spylab/agentdojo) · observed Sep 20, 2026
- Last push (ethz-spylab/agentdojo) · observed Jun 2, 2026
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (glo26/stepshield) · observed Sep 20, 2026
- GitHub forks (glo26/stepshield) · observed Sep 20, 2026
- Last push (glo26/stepshield) · observed Sep 5, 2026
- License file (Other) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 16, 2026
- Trust scan (lockfile / OSV) · observed Jul 15, 2026
GitHub stars on cards: agentdojo 802 · stepshield 76 (synced Sep 20, 2026).
Common questions
- What is the difference between agentdojo and stepshield?
- agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. stepshield: Temporal evaluation benchmark for AI agent guardrails. See the comparison table for live GitHub stats and shared categories.
- When should I choose agentdojo over stepshield?
- Choose agentdojo over stepshield when License: agentdojo is MIT, stepshield is Other; Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs.; Requirements: Min 8 GB RAM; Tags unique to agentdojo: large-language-models, prompt-injection, security; AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
- When should I choose stepshield over agentdojo?
- Choose stepshield over agentdojo when License: stepshield is Other, agentdojo is MIT; Tags unique to stepshield: agent-security, ai-safety, dataset, guardrails; When you need to measure the timing of interventions rather than just if they occur.
- When should I avoid agentdojo?
- Last GitHub push was Jun 2, 2026 (slowing maintenance). Validate activity before betting a new project on agentdojo. AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
- When should I avoid stepshield?
- If your project does not require temporal analysis of guardrail performance When you seek real-time intervention and do not need pre-defined trajectory datasets
- Is agentdojo or stepshield more popular on GitHub?
- agentdojo has more GitHub stars (802 vs 76). Stars measure visibility, not whether either tool fits your constraints.
- Are agentdojo and stepshield open source?
- Yes - both are open-source projects on GitHub (agentdojo: MIT, stepshield: Other).
- Where can I find alternatives to agentdojo or stepshield?
- GraphCanon lists graph-backed alternatives at agentdojo alternatives and stepshield alternatives (agentdojo markdown twin, stepshield markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, agentdojo or stepshield?
- agentdojo: Slowing. stepshield: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for agentdojo and stepshield?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: agentdojo trust report; stepshield trust report.