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.
- arXiv · Published · First archived
Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents ↗
Autonomous coding agents now resolve a substantial share of real-world GitHub issues. However, passing functional tests differs fundamentally from producing a high-quality contribution acceptable for merging. Mature open-source projects publish repository-specific contribution policies, spanning style, git, testing workflows, to ensure code quality and long-term maintainability. Because existing benchmarks evaluate patches solely on unit tests, agent compliance with repository governance remains unknown. In this paper, we introduce SWE-CC, a benchmark evaluating code and process compliance in…
- GitHub · Repository created · First archived
Grit-77/done-is-a-claim ↗
Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.
- GitHub · Repository created · First archived
bottomless/agent-duel ↗
Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.
- GitHub · Repository created · First archived
autohandai/getzit ↗
Zit: a git extension that lets developers and coding agents change one repository at the same time without stepping on each other's toes, and it's kind to your SSD.
- GitHub · Repository created · First archived
LambdaLabsHQ/xmatrix ↗
Group chat for humans and coding agents. Mention @claude, @codex, @cursor or @gemini in a channel: the agent runs on your machine with your own subscription and keeps the team's pages current.
- GitHub · Repository created · First archived
lcandy2/sim-agentation ↗
Annotate a running iOS simulator in your browser, and hand the notes to your coding agent.
- Hacker News · Posted on Hacker News · First archived
Show HN: Stateful Linux microVMs for coding agents ↗
I always wanted to have fly.io's sprite "at home" or orbs or whatever else there is. The VMs are based on libkrun. There is also an option of replicated storage (based on S3/R2 API): https://ahvm.app/docs/#replicated-storage Still in progress. Trash it. Yes I used AI.
- GitHub · Repository created · First archived
openfilm/openfilm ↗
The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything it makes.
- GitHub · Repository created · First archived
djtoon/pi-forge ↗
The harness that builds harnesses: tell it about your work and it builds a custom AI agent with its own tools, views, skills and UI. Runs in the browser, terminal, headless, or as a standalone app. Built on pi.
- Hacker News · Posted on Hacker News · First archived
MBTI for AI coding agents, complete with a self-awareness score ↗
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.