Findings, fragments, tasks, truths, skills, and sessions across machines. Private markdown. Git-backed. No database.
~/.phren, wires MCP, installs hooks.
phren add from any repo.phren init picks it up.Phren catches findings, links fragments across projects, and figures out what matters. Gets sharper over time.
Git syncs after every response, pulls on open. Your knowledge travels with you, not your machine.
Interactive shell, web UI, and VS Code sidebar. Browse findings, fragments, and the full knowledge graph. Search across projects.
CLAUDE.md dumps everything every time. Phren searches, ranks, and surfaces only what matches. About 550 tokens instead of the whole file. Less noise, lower cost.
Switch agents, switch machines. Phren keeps up. What you figured out in Claude this morning is already there when you open Cursor tonight. Good stuff sticks. Bad stuff fades.
Team stores are shared git repos with phren-structured data. Your team's findings sync automatically. Personal knowledge stays private. One command to join.
Claude asks a question. Phren already looked it up. The findings, the gotchas, the thing that broke last time. All there before the first token.
Browse what phren knows. Check on tasks. Review the queue. Type : for the command palette.
Run phren web-ui to open a visual map of everything phren holds. Findings, connections, quality scores, and what needs your attention.
Projects, findings, tasks, fragments, skills, hooks, sessions, and the interactive knowledge graph. Search, add, review, and push. All from the sidebar.
Projects, findings, tasks, skills, hooks, sessions. All browsable.
Interactive webview. Click nodes, explore connections, edit findings in-graph.
Search phren's knowledge base without leaving your editor.
MCP tools handle search, capture, review, and sync. Skills are shortcuts for larger jobs. Global skills live in ~/.phren/global/skills/, project skills in ~/.phren/<project>/skills/. Project skills override global ones with the same name.
~/.phren/global/skills/~/.phren/<project>/skills/MCP and hooks. Same knowledge, same findings, no matter which tool you're in.
No API calls. No third party.
Findings tagged with sessions, linked to tasks, surfaced before every prompt.