Works with
848 tests
Enterprise tested
Claude CodeCodexGeminiCopilotCursorAmpClineRoo Code
848 tests
Enterprise tested
SessionFS captures your AI coding sessions and makes them portable, searchable, and verifiable across tools and teammates.
| ID | Tool | Msgs | |
|---|---|---|---|
| ses_a1b2 | claude-code | 47 | Debug auth token refresh |
| ses_c3d4 | codex | 31 | Refactor database schema |
| ses_e5f6 | gemini | 23 | Add rate limiting middleware |
| ses_g7h8 | copilot | 15 | Fix CI pipeline YAML |
| ses_i9j0 | cursor | 52 | Implement OAuth2 flow |
| ses_k1l2 | amp | 18 | Write migration script |
| ses_m3n4 | cline | 9 | Setup Docker compose |
| ses_o5p6 | roo-code | 27 | API endpoint tests |
848 tests
Enterprise tested
Three commands. Under a minute. Zero behavior change.
Sessions captured from 8 tools automatically. No config needed.
Browse sessions across all tools in one unified view.
Resume any session in any supported tool. Full context preserved.
Your sessions are no longer locked to a single tool.
Push to the cloud, pull on any machine. Auto-sync available.
Hand off sessions with full context. Session data copies to recipient.
Full-text search across all sessions. Find that fix from last week.
Your AI agent remembers past sessions and project context via MCP.
Catch what the AI got wrong. Severity-classified findings with evidence.
See what happened in 10 seconds. Files, tests, commands — extracted automatically.
AI session context on every PR and MR. Contradictions surfaced for reviewers.
Git state captured automatically. Branch, commit, dirty files — all recorded.
The LLM Judge cross-references every AI claim against actual tool outputs. When the AI says "the test passes" but the exit code was 1 — that's a critical contradiction, flagged with full evidence.
Severity-classified findings: CRITICAL for test failures and failed commands. HIGH for file mismatches and data misreads. Every finding links to the exact message.
BYOK — your key, never stored. Works with any OpenAI-compatible endpoint: OpenRouter, LiteLLM, vLLM, Ollama.
Read the docs →Full conversation context, workspace state, and tool configs transfer instantly between teammates.
Paths auto-resolve by git remote URL. No manual configuration.
Every session automatically summarized — files changed, tests run, commands executed, key decisions made. No more reading 2,000 messages to understand what the AI did.
Deterministic extraction runs instantly with no LLM cost. Optional LLM narrative adds "what happened" and "key decisions" sections.
Self-hosted Kubernetes deployment with Helm. Your data stays on your infrastructure.
Deploy to any Kubernetes cluster — AWS EKS, GCP GKE, or on-prem. Helm chart, enterprise-tested.
AI session context on every PR (GitHub) and MR (GitLab). Audit findings surfaced inline for reviewers.
Bring your own LLM — Anthropic, OpenAI, Google, or any OpenAI-compatible endpoint.
Local capture, cloud sync, team handoff, session search, MCP, and LLM Judge — all included. No credit card. No limits.
Paid plans with storage-based pricing are coming after beta.