THE INTERNET IS THINKING
Earlier sources: AI agents
AI agents use models to choose actions, call tools, and work toward a goal. This thread follows agent frameworks, memory, orchestration, evaluation, and safeguards; autonomy and reliability vary between systems.
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 ↗844 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
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks ↗
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle verifier, both of which require prior knowledge of the environment. We present DAEDALUS, a method for bootstrapping reusable agent memory from self-generate…
- GitHub · Repository created · First archived
tedix-hq/tedix ↗
Open-source AI coworkers for your team. They do recurring work, ask before risky steps, and show you exactly what they did.
- Hacker News · Posted on Hacker News · First archived
Two Types of AI Agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Manage Skills, Memories, and Agents.md Files Across Tools and Projects ↗
I work with different AI coding tools, including codex, Claude,, Opencode, cursor, and others. Also, I work on several projects under different folders. This makes managing skills, AGENTS.md files, MCPs so hard. I'm not sure what is installed where. Also, agents create memory files nowadays with instructions that I find misleading, so i wanna read and edit these memory files occasionally. Thats why I created a tool with proper UI to manage all of…
- Hacker News · Posted on Hacker News · First archived
Bringing predictive analytics to the agentic AI era ↗
Hacker News discussion.
- GitHub · Repository created · First archived
electric-dragon-80000v/pi-cowboy ↗
Herdr-native agent orchestrator for Pi. Can run Codex, Claude Code, OpenCode and more as subagents in isolated copy-on-write git worktrees.
- Hacker News · Posted on Hacker News · First archived
Autolith: A self-modifiable general purpose Lisp AI agent ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Autonomous AI Agent Security Incidents of 2026 (Dataset and Defense Harness) ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Plainserp – Google search API for AI agents at $0.30 per 1k ↗
Hacker News discussion.
- GitHub · Repository created · First archived
zanedonkey/dsh-tool-12306 ↗
Native China Railway 12306 query tools for DeepSeek Harness.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI 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.