Komi-learn – continuous memory and self-improvement for coding agents
Continuous memory + self-improvement for AI agents. Learns how you work, recalls it automatically, no commands. Claude Code & Codex. - kurikomi-labs/komi-learn
Komi-learn – continuous memory and self-improvement for coding agents launched on May 31, 2026 with 27 votes, #842 of 20,538 launches that month and more than 95% of that year's launches.
In plain words
Komi-learn is a development tool that provides continuous memory and self-improvement capabilities for coding agents. It enables these agents to learn from past interactions and progressively enhance their performance over time. The tool is designed for developers working with AI-powered code generation and automation systems. Its distinguishing feature is the ability to maintain persistent memory while continuously iterating on agent behavior, making it useful for creating more capable and adaptive coding assistants.
written from the facts on this page · September 2026
From the sources
Coding agents forget everything between sessions. komi-learn gives yours continuous memory: it learns your stack and style in the background and recalls it automatically next session. No commands, runs locally. Works with Claude Code and Codex. Open source.
Continuous memory and self-improvement for coding agents. It learns how you work and recalls it automatically, with no commands. Works with Claude Code and Codex. It watches a session, distills durable lessons in the background (your style, your stack, fixes that worked), and loads the relevant ones at the start of the next session. No slash commands, nothing to save by hand. The idea is from Hermes Agent ; this is my own take, generalized across hosts with an optional shared layer (the community pool, below). It's early. The core loop is built and CI-tested, but it hasn't been battle-tested across a lot of real sessions yet. Feedback and bug reports are welcome. pip install komi-learn…from github.com
Does a similar job
all alternatives →
remio2025 · remio.ai · ▲541remio is designed to free you from being a manual data porter for AI. By syncing your full context, it builds a zero-effort Second Brain that understands your work as well as you do. We call this AI knowledge base "remio", because we want to build a local first app to "remember every input and output". As knowledge workers, we are stuck copy-pasting context just to get a decent answer. We spend more time digging through scattered Slack threads, Google Docs, and local files than actually doing the work. So here is what we made: 1. Connect once: It automatically indexes your full context—web…
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: Show HN post ↗
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