This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
DevRecall
On-device memory for everything you ship
Most tools that remember your work ship it to someone's cloud. DevRecall keeps a searchable index of your whole work history on your laptop — local SQLite, offline embeddings, nothing leaves the machine. It pulls from Git, GitHub, Slack, Jira, Linear and Confluence, then links each ticket to the commits, PRs and threads that resolved it. Ask "what was that auth bug in February?" and answers cite real rows. Also an MCP server, so Claude Code and Cursor recall your history inline. MIT.
I kept hitting the same wall: someone asks what I worked on last quarter, and I'm scrolling git log, Jira, and Slack trying to reconstruct it. The tools that solve this are mostly built for managers — dashboards that ingest your org's data into their cloud to measure teams. I wanted the opposite: something for me, that indexes the systems of record I actually work in, and never leaves my laptop.
So DevRecall does it entirely on-device. It pulls from Git, GitHub/GitLab, Slack, Calendar, Jira, Linear and Confluence into a local SQLite database, and everything — search, embeddings, grouping — runs on your machine. The only cloud piece is a Cloudflare Worker that forwards OAuth callbacks; it never sees your data.
Two things I'm most happy with:
Tickets linked to code. It extracts issue keys from commit messages and branch names, then groups a ticket with the commits, PRs and discussions that resolved it. "What happened with PROJ-123?" returns one timeline across all your sources — and that join is deterministic, no LLM guessing.
Memory for your coding agent. It ships an MCP server, so Claude Code, Cursor, Codex, Continue or Zed can search your work history inline, with citations.
Search fuses keyword and semantic matching, so a vague "stale sessions after a password change" finds the right work even with no exact keyword overlap. Answers always cite the rows they read — nothing invented.
Happy to answer anything — especially curious what sources people want next.
About DevRecall on Product Hunt
“On-device memory for everything you ship”
DevRecall was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #124 on the daily leaderboard. Most tools that remember your work ship it to someone's cloud. DevRecall keeps a searchable index of your whole work history on your laptop — local SQLite, offline embeddings, nothing leaves the machine. It pulls from Git, GitHub, Slack, Jira, Linear and Confluence, then links each ticket to the commits, PRs and threads that resolved it. Ask "what was that auth bug in February?" and answers cite real rows. Also an MCP server, so Claude Code and Cursor recall your history inline. MIT.
On the analytics side, DevRecall competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how DevRecall performed against the three products that launched closest to it on the same day.
Who hunted DevRecall?
DevRecall was hunted by Pavel Piliak. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of DevRecall including community comment highlights and product details, visit the product overview.
Pavel Piliak
Hey Product Hunt 👋
I kept hitting the same wall: someone asks what I worked on last quarter, and I'm scrolling git log, Jira, and Slack trying to reconstruct it. The tools that solve this are mostly built for managers — dashboards that ingest your org's data into their cloud to measure teams. I wanted the opposite: something for me, that indexes the systems of record I actually work in, and never leaves my laptop.
So DevRecall does it entirely on-device. It pulls from Git, GitHub/GitLab, Slack, Calendar, Jira, Linear and Confluence into a local SQLite database, and everything — search, embeddings, grouping — runs on your machine. The only cloud piece is a Cloudflare Worker that forwards OAuth callbacks; it never sees your data.
Two things I'm most happy with:
Tickets linked to code. It extracts issue keys from commit messages and branch names, then groups a ticket with the commits, PRs and discussions that resolved it. "What happened with PROJ-123?" returns one timeline across all your sources — and that join is deterministic, no LLM guessing.
Memory for your coding agent. It ships an MCP server, so Claude Code, Cursor, Codex, Continue or Zed can search your work history inline, with citations.
Search fuses keyword and semantic matching, so a vague "stale sessions after a password change" finds the right work even with no exact keyword overlap. Answers always cite the rows they read — nothing invented.
Happy to answer anything — especially curious what sources people want next.