Comparison
agentdojo vs Aegis
Verdict
Unverified catalog guidance: agentdojo: AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. Aegis: Aegis provides runtime policy enforcement for AI agents with cryptographic audit trails and human-in-the-loop approvals, supporting zero-code deployment switches suited for various compliance needs.
Markdown twin · agentdojo alternatives · Aegis alternatives
GraphCanon updated Oct 19, 2026
Trust & integrity
| Signal | agentdojo | Aegis |
|---|---|---|
| Maintenance | Slowing (125d since push) As of Oct 6, 2026 · github_public_v1 | Active (10d since push) As of Oct 19, 2026 · github_public_v1 |
| Provenance | Not a fork · Organization account As of Oct 6, 2026 · github_public_v1 | Not a fork · Personal account As of Oct 19, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 | No lockfile (source not queried) 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
- Aegis
- Runtime policy enforcement for AI agents with cryptographic audit trail and human-in-the-loop approvals.
Stars
- agentdojo
- 893
- Aegis
- 542
Forks
- agentdojo
- 235
- Aegis
- 52
Open issues
- agentdojo
- 72
- Aegis
- 4
Language
- agentdojo
- Python
- Aegis
- TypeScript
Adopt for
- agentdojo
- Unverified catalog guidance: AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
- Aegis
- Unverified catalog guidance: Aegis provides runtime policy enforcement for AI agents with cryptographic audit trails and human-in-the-loop approvals, supporting zero-code deployment switches suited for various compliance needs.
Persona
- agentdojo
- -
- Aegis
- -
Runtime
- agentdojo
- -
- Aegis
- -
License
- agentdojo
- MIT
- Aegis
- MIT
Last pushed
- agentdojo
- Jun 2, 2026
- Aegis
- Oct 9, 2026
Categories
- agentdojo
- AI Agents, Evaluation & Observability
- Aegis
- AI Agents, Evaluation & Observability
Trust and health
Maintenance
- agentdojo
- Slowing (36%)
- Aegis
- Active (82%)
Days since push
- agentdojo
- 125d
- Aegis
- 10d
Open issues (recorded)
- agentdojo
- 72
- Aegis
- 4
Stars delta
- agentdojo
- +91 (30d)
- Aegis
- +202 (30d)
Open issues delta
- agentdojo
- +21 (30d)
- Aegis
- +1 (30d)
Owner type
- agentdojo
- Organization
- Aegis
- User
Full report
- agentdojo
- Trust report
- Aegis
- Trust report
Choose agentdojo if…
- agentdojo is primarily Python; Aegis is TypeScript.
- 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: benchmark, large-language-models, prompt-injection, security.
- Unverified catalog guidance: 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 Aegis if…
- Aegis is primarily TypeScript; agentdojo is Python.
- Tags unique to Aegis: ai-safety, anthropic, audit-trail, llm-observability.
- Unverified catalog guidance: You need cryptographic assurance of the audit trail to meet high-security standards.
When NOT to use Aegis
- Unverified catalog guidance: The project does not require a zero-code deployment switch and can manage changes directly in the codebase.
- Unverified catalog guidance: Minimal regulatory requirements mean that elaborate configurations like Aegis's strict retention policies are unnecessary.
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 Oct 6, 2026
- GitHub forks (ethz-spylab/agentdojo) · observed Oct 6, 2026
- Last push (ethz-spylab/agentdojo) · observed Jun 2, 2026
- License file (MIT) · observed Oct 6, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (Justin0504/Aegis) · observed Oct 19, 2026
- GitHub forks (Justin0504/Aegis) · observed Oct 19, 2026
- Last push (Justin0504/Aegis) · observed Oct 9, 2026
- License file (MIT) · observed Oct 19, 2026
- Decision facts (enrichment) · observed Jul 16, 2026
- Trust scan (lockfile / OSV) · observed Jul 15, 2026
GitHub stars on cards: agentdojo 893 · Aegis 542 (synced Oct 6, 2026).
Common questions
- What is the difference between agentdojo and Aegis?
- agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. Aegis: Runtime policy enforcement for AI agents with cryptographic audit trail and human-in-the-loop approvals.. See the comparison table for recorded GitHub metadata and shared categories.
- When should I choose agentdojo over Aegis?
- For agentdojo, compare these recorded points with Aegis: agentdojo is primarily Python; Aegis is TypeScript; 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: benchmark, large-language-models, prompt-injection, security; Unverified catalog guidance: 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 Aegis over agentdojo?
- For Aegis, compare these recorded points with agentdojo: Aegis is primarily TypeScript; agentdojo is Python; Tags unique to Aegis: ai-safety, anthropic, audit-trail, llm-observability; Unverified catalog guidance: You need cryptographic assurance of the audit trail to meet high-security standards.
- 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 Aegis?
- Unverified catalog guidance: The project does not require a zero-code deployment switch and can manage changes directly in the codebase. Unverified catalog guidance: Minimal regulatory requirements mean that elaborate configurations like Aegis's strict retention policies are unnecessary.
- Is agentdojo or Aegis more popular on GitHub?
- agentdojo has more recorded GitHub stars (893 vs 542). Stars measure visibility, not whether either tool fits your constraints.
- Which licenses are recorded for agentdojo and Aegis?
- agentdojo: MIT. Aegis: MIT. Check each repository's current license and terms before use. Public GitHub hosting alone does not establish open-source licensing.
- Where can I find alternatives to agentdojo or Aegis?
- GraphCanon lists candidates at agentdojo alternatives and Aegis alternatives (agentdojo markdown twin, Aegis markdown twin). The discovery order uses stored relationship proposals and shared categories; it is not a verified replacement ranking.
- 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 Aegis?
- agentdojo: Slowing. Aegis: 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 Aegis?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: agentdojo trust report; Aegis trust report.