Metacog
Stops your agents repeating the same mistakes.
What it does
AI coding agents can't feel when they're stuck. They'll retry the same broken fix five times because they can see each error but not the pattern. Metacog is a Claude Code hook that watches for these loops, and six other failure modes, silently. When things go wrong, it nudges the agent to reflect. When problems resolve, it learns what fixed them. Most memory systems prune rules that stop firing. Metacog treats that silence as proof the rule worked. Zero dependencies. One-command install.
Does the same job
all alternatives →
AgentmemoryMay 2026 · agent-memory.dev · ▲322Persistent memory for Claude Code, Codex & coding agents
- SCStop Claude Code from forgetting everythingDec 2025 · github.com · ▲202
I got tired of Claude Code forgetting all my context every time I open a new session: set-up decisions, how I like my margins, decision history. etc. We built a shared memory layer you can drop in as a Claude Code Skill. It’s basically a tiny memory DB with recall that remembers your sessions. Not magic. Not AGI. Just state. Install in Claude Code: /plugin marketplace add https://github.com/mutable-state-inc/ensue-skill /plugin install ensue-memory # restart Claude Code What it does: (1) persists context between sessions (2) semantic & temportal search (not just…
- IBI built a tool to assist AI agents to know when a PR is good to goJan 2026 · dsifry.github.io · ▲45
I've been using Claude Code heavily, and kept hitting the same issue: the agent would push changes, respond to reviews, wait for CI... but never really know when it was done. It would poll CI in loops. Miss actionable comments buried among 15 CodeRabbit suggestions. Or declare victory while threads were still unresolved. The core problem: no deterministic way for an agent to know a PR is ready to merge. So I built gtg (Good To Go). One command, one answer: $ gtg 123 OK PR #123: READY CI: success (5/5 passed) Threads: 3/3 resolved It aggregates CI status, classifies review comments…
- MAMeta-agent: self-improving agent harnesses from live tracesApr 2026 · github.com · ▲14
We built meta-agent: an open-source library that automatically and continuously improves agent harnesses from production traces. Point it at an existing agent, a stream of unlabeled production traces, and a small labeled holdout set. An LLM judge scores unlabeled production traces as they stream. A proposer reads failed traces and writes one targeted harness update at a time, such as changes to prompts, hooks, tools, or subagents. The update is kept only if it improves holdout accuracy. On tau-bench v3 airline, meta-agent improved holdout accuracy from 67% to 87%. We open-sourced meta-agent.…
- SPSimple plugin to get Claude Code to listen to youMar 2026 · gopeek.ai · ▲18
Hey HN, My cofounder and I have gotten tired of CC ignoring our markdown files so we spent 4 days and built a plugin that automatically steers CC based on our previous sessions. The problem is usually post plan-mode. What we've tried: Heavily use plan mode (works great) CLAUDE.md, AGENTS.md, MEMORY.md Local context folder (upkeep is a pain) Cursor rules (for Cursor) claude-mem (OSS) -> does session continuity, not steering We use fusion search to find your CC steering corrections. - user prompt embeddings + bm25 - correction embeddings + bm25 - time decay - target query embeddings -…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
