#4343rd of 89 in Agent platforms
tracecat
Security automation platform with workflows, case management and AI agents
- Stars
- 3.9k
- License
- AGPL-3.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
3,547 on 22 Apr 20263,906 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Tracecat is a security automation platform that combines a workflow builder running on Temporal, case management, structured tables, and agents with tools, subagents and skills. It ships 100+ connectors and 50+ hosted MCP servers for security tools, and can act as an MCP client. The backend is Python/FastAPI with PostgreSQL and an S3-compatible object store, and untrusted code runs in nsjail sandboxes.
Who it is for: Security teams automating incident response and triage with agents
Strengths
- Workflows run on Temporal, giving durable execution and resilience
- Includes case management and tables alongside workflows and agents
- SAML/OIDC and exportable audit logs are in the open-source edition
- Can run fully air-gapped; untrusted code runs in nsjail sandboxes
Weaknesses
- Multi-tenancy, RBAC/ABAC and human-in-the-loop approvals are Enterprise-only
- Code in packages/tracecat-ee cannot be used in production without a license
- AGPL-3.0 license may be a problem for some commercial use
- Needs Temporal, PostgreSQL and S3-compatible storage, so deployment has many parts
What it needs
- Docker + Compose
- Needs Temporal, PostgreSQL, S3-compatible object store
What changed
“refactor(agents)!: Rename the chat backend setting to session backend (#4066)”
“fix(agents): Require agent:update for the preset builder chat (#4056)”
“fix(api)!: Scope user email search to the caller's organization (#3862)”
“security(deps): Patch Next.js image RCE, DOMPurify, OTel, virtualenv (#3965)”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent platforms
See all 89| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |