Hey HN! OP here.

I built ContextLedger because I kept losing context between AI coding sessions. I'd wrap up a session with Claude or Codex, and the next day I'd spend the first 10 minutes re-explaining what I was working on, what failed, and what was left to do.

ContextLedger is a local-first CLI that captures events from your AI coding sessions (prompts, tool use, errors, files touched), summarizes them into structured "capsules," and generates resume packs / handoff documents so your next session starts with the right context already loaded.

Key design choices:

Local-first, SQLite-backed – everything stays on your machine. No cloud, no accounts.

Multi-agent – works with Claude Code (via hook events), Codex (rollout JSONL ingestion), and Gemini (coming soon!).

Privacy controls – prompt capture is off by default, secrets are redacted, and you can block prompt content from being sent to remote summarizers.

Summarizer-agnostic – supports local models via Ollama, or OpenAI/Anthropic APIs for generating session capsules and intent labels.

Handoff workflow – ctx-ledger handoff --agent claude --from latest generates context and can launch the agent directly with it injected.

It also ships with a web dashboard (ctx-ledger dashboard) that gives you a live view of your active agents and detailed analysis of your sessions — planning vs. execution time breakdowns, project-level time tracking, intent distribution, and tool usage stats. It auto-refreshes every few seconds and keeps syncing enabled integrations in the background, so it doubles as a monitoring panel while you work. The onboard command gets you set up in one step – it enables integrations, runs an initial sync, and starts the dashboard.

I've been using it daily for last few days and it's made a noticeable difference in how quickly I can pick up where I left off, especially on multi-day projects. The intent labeling and planning-vs-execution time breakdowns have also been interesting for understanding how I actually use these tools. Would love feedback.

Repo: https://github.com/manthan787/context-ledger

I'm interested in the intent classification breakdown shown in the dashboard screenshot. That's cool, I'd love to know what's the breakdown b/w various types of tasks I accomplish with Claude code. Pretty cool!

Thanks, glad that caught your eye! The summarizer tags each session with a hierarchical intent label (e.g. `coding/frontend`, `research/tech-qna`, `deploy`) and a confidence score. You can run it fully local with Ollama so nothing leaves your machine. Would love to hear any feedback when you try it out

Thanks! We’re still super early and fixing things as we go. Hope you’ll keep trying it, more features coming very soon!

One should really read Julian Assange's views on Schmidt and Google's think tank. It seems like he got it right.

Here's the link to the article: http://www.newsweek.com/assange-google-not-what-it-seems-279...

Interesting read.

"Schmidt arrived first, accompanied by his then partner, Lisa Shields. When he introduced her as a vice president of the Council on Foreign Relations—a U.S. foreign-policy think tank with close ties to the State Department—I thought little more of it. Shields herself was straight out of Camelot, having been spotted by John Kennedy Jr.’s side back in the early 1990s.

...

Some time later Jared Cohen arrived. With him was Scott Malcomson, introduced as the book’s editor. Three months after the meeting Malcomson would enter the State Department as the lead speechwriter and principal advisor to Susan Rice (then U.S. ambassador to the United Nations, now national security advisor).

...

I knew little else about Cohen at the time. In fact, Cohen had moved to Google from the U.S. State Department in 2010. He had been a fast-talking “Generation Y” ideas man at State under two U.S. administrations, a courtier from the world of policy think tanks and institutes, poached in his early twenties.

He became a senior advisor for Secretaries of State Rice and Clinton. At State, on the Policy Planning Staff, Cohen was soon christened “Condi’s party-starter,” channeling buzzwords from Silicon Valley into U.S. policy circles and producing delightful rhetorical concoctions such as “Public Diplomacy 2.0.” On his Council on Foreign Relations adjunct staff page he listed his expertise as “terrorism; radicalization; impact of connection technologies on 21st century statecraft; Iran.”"

What I get from this is that Schmidt has (had?) very deep links into the US State Department.

This was new to me so thanks.

Yes, I was amazed too. He also published the whole 2 hours+ long audio recording of the whole thing. So you can actually listen to the whole thing, the things he is referring to in the article.