Smriti
Git for reasoning state across coding agents
Smriti launched on May 25, 2026 with 3 votes, #3,449 of 20,538 launches that month and more than 50% of that year's launches.
What it does
Smriti is an early open-source layer for versioning project reasoning across Claude Code, Codex, Cursor and other coding agents. Agents can share state, claim work, checkpoint decisions, detect repo drift and continue from each other’s work. Built to reduce handoff chaos when switching models or running multiple agents on one codebase.
Code has Git. Multi-agent reasoning does not. Smriti is version control for project reasoning state — versioned, structured, branchable snapshots so multiple coding agents coordinate on the same codebase without overwriting each other
Smriti is version control for project reasoning state. Versioned, structured, branchable snapshots of what was decided , what's still open , and what each agent is doing right now — so multiple coding agents coordinate on the same codebase without overwriting each other's thinking. A single human committing serial code has Git. Multiple agents writing reasoning state in parallel have nothing. Smriti closes the gap with the same primitives, plus three Git was never built to have. The last three have no Git equivalent. Git is built for one human committing serial code. Smriti is built for multiple agents writing reasoning state in parallel. A shared markdown file works until two agents need…from smritistate.dev
Does a similar job
all alternatives →
StraionFeb 2026 · straion.com · ▲376Hi HN — we’re building Straion (founders are ex‑Netlify, ex‑Elastic, ex‑Dynatrace). Core idea: static AGENTS.md / CLAUDE.md files are useful, but they often become too broad for real tasks. Instead of injecting all guidance every time, Straion selects the relevant rules per task and keeps context narrow. How it works today: 1. You define org/team/project rules centrally 2. A CLI skill calls our pipeline during agent workflows 3. Straion returns only the rules relevant to the current task 4. The agent gets focused context instead of a giant rules dump This reduces context bloat…
Git for AI AgentsMay 2026 · github.com · ▲129hi guys. been working on something i think is fundamentally missing in today's workflow with ai agents. vcs. i find myself struggling with questions that agents can't answer like "why did you do it?", "when did u delete this folder? why?", etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session. just like git did for code, i think we are the same core capabilities with ai agents so... i developed an open source solution for that (currently supporting claude code) would love to…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com