diff --git a/website/index.html b/website/index.html index 8faf8ec..7f55b22 100644 --- a/website/index.html +++ b/website/index.html @@ -4,10 +4,10 @@
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.
The missing primitive
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 threehave no Git equivalent. Git is built for one human committing serial code. Smriti is built for multiple agents writing reasoning state in parallel. +
Why HANDOFF.md isn't enough
HANDOFF.md
A shared markdown file works until two agents need to edit it at once, ask "is my base still current?", or compare two takes on the same decision. The moment coordination needs to be queried, branched, or validated against the repo, prose stops working.
What Smriti is
Smriti is a small backend, a CLI, an MCP server, and skill packs for Claude Code and Codex. It records structured snapshots at inflection points — not a running log of everything an agent saw — and exposes them as a queryable state brief every agent reads at session start.
One Space per project. Per-project attachment via .smriti.json. Local SQLite by default; Postgres for shared/team workflows. No orchestrator. No router. No assignment logic. Agents read the same structured state and decide for themselves.
.smriti.json
One Space per project. Per-project attachment via .smriti.json. Local SQLite by default; Postgres for shared workflows. No orchestrator. No router. No assignment logic. Agents read the same structured state and decide for themselves.
The hard part isn't storing reasoning — it's making it self-validating against the live repo and safe for parallel writers. That's the work.
.nojekyll
Multi-agent coordination — protocol, not orchestration
Multi-agent coordination · protocol, not orchestration
Each agent reads the shared state, sees the others' active claims, and picks something complementary. The "routing logic" is structured metadata, not a queue manager.
+ Click any unclaimed packet to fire it manually click +
This is the actual pattern that built this site. Same task pool, two agents, complementary picks, no human routing. smriti metrics smriti-dev below shows the cumulative coordination cost — 87 claims, 97% completion, 67 cross-agent continuations.
smriti metrics smriti-dev
This is the pattern that built this site. Same task pool, two agents, complementary picks, no human routing. smriti metrics smriti-dev below shows the cumulative coordination cost.
Drift & trust
A reasoning snapshot is only useful if it tracks the code it's reasoning about. Every checkpoint records the repo HEAD and branch. Every state brief compares it back to the live repo — and surfaces the drift before another agent acts on stale ground.
Built with Smriti
Claude Code and Codex co-built this project end-to-end through Smriti's own state. Real numbers from the project Space, as of today:
The 67 cross-agent continuations are the headline. Each is a moment where one agent ended a session, the other started, read the shared state, and continued the same thread as if it had been there for the work.
Try it
No Docker, no API keys, no cloud required. The core coordination loop runs on a local SQLite file. API keys come in only for optional LLM-assisted features.
git clone https://github.com/himanshudongre/smriti -cd smriti -make setup-local -make dev-local # backend, leave running
git clone https://github.com/himanshudongre/smriti +cd smriti +make setup-local +make dev-local # backend, leave running
cd smriti -source backend/.venv/bin/activate + +cd smriti +source backend/.venv/bin/activate -smriti doctor # verify install -smriti quickstart # seeded demo Space + 3-min walkthrough - After the walkthrough, cd into any of your own projects and run smriti init my-project to attach it. One Space per project. +smriti doctor # verify install +smriti quickstart # seeded demo + 3-min walkthrough + + After the walkthrough, cd into any of your own projects and run smriti init my-project to attach it. One Space per project. +
cd smriti +source backend/.venv/bin/activate -smriti doctor # verify install -smriti quickstart # seeded demo Space + 3-min walkthrough
After the walkthrough, cd into any of your own projects and run smriti init my-project to attach it. One Space per project.
cd
smriti init my-project