THE INTERNET IS THINKING
Earlier sources: AI coding agents
AI coding agents use models and development tools to inspect, modify, and test software. Follow coding workflows, repository tooling, evaluations, and evidence about where these systems succeed or fail.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗85 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- Hacker News · Posted on Hacker News · First archived
Show HN: shadowclone, skills learned from your coding agent corrections ↗
shadowclone reads the coding-agent sessions already on your disk, finds where you corrected the agent and turns those corrections into skills your agents load next time. It supports Claude Code, Codex, Cursor, Pi, and Antigravity. Every capture source is off by default and has its own consent setting. Why I'm building it? I use multiple harnesses and agents, I extensively use Claud Code and Codex, but I also use Cursor and Antigravity every now a…
- GitHub · Repository created · First archived
damian-kolasinski/mergegate ↗
Local code review hub for AI coding agents (Claude Code, Codex, Cursor, opencode). Agents submit with one CLI, you review files ranked by importance, feedback flows back. GitHub or plain git.
- Hacker News · Posted on Hacker News · First archived
Show HN: A 3D sky city where my Claude Code agents work and take coffee breaks ↗
Open source, local and no telemetry.
- GitHub · Repository created · First archived
vakandi/opencode-rust ↗
The open source AI coding agent, in Rust. CLI, TUI and HTTP server for local AI agents — no Docker required.
- GitHub · Repository created · First archived
Antarsoft/morphness ↗
Self-improving multi-agent harness for Claude Code. A Technical Lead plans, Full-stack builds, QA verifies, and retros turn lessons into rules that fit your project. Stack-agnostic.
- GitHub · Repository created · First archived
Generated-Computers/Locals ↗
Run many AI agents at once on your Mac, about three times faster.
- Hacker News · Posted on Hacker News · First archived
Show HN: An OpenAI-compatible API that coding agents sign up for themselves ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
A hub that controls all your coding agents in one place ↗
i usually have several coding agents running at once (who doesnt nowadays?); claude code, codex, grok and none of them knows what they are working on. if codex figures something out, i want claude to know it, I'm the one copying it across. i built agent-mesh which acts a hub for these agents. every agent that loads it joins a small hub that runs as your user. from there it can: - list other live agent sessions on your machine, message them, read…
- GitHub · Repository created · First archived
larstalian/tincan ↗
Your team's coding agents talking to each other across machines: a live directory of who's working on what, plus messages. Peer to peer, no server.
- Hacker News · Posted on Hacker News · First archived
Long-term memory for AI coding agents as a tree of plain files ↗
Hacker News discussion.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI coding agents
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.