AGENTS
92 items
55 posts, 28 tools, 9 guides
InsForge is an open-source backend for agentic coding. Why agents still break databases, auth and deploys, and what an agent-readable control plane needs.
Open-source (MIT) terminal coding agent, renamed Codewhale, with Plan, Work, and Operate modes, approval postures, /undo and /restore, receipts, MCP servers, sub-agents, and a local runtime HTTP API. Provider-neutral: 40+ built-in provider routes plus local models, no longer DeepSeek by default.
Agent swarms are easy to launch and hard to trust. Why every multi-agent setup needs receipts - tests, logs, diffs and reviewable checkpoints - not more agents.
SNEWPAPERS is a useful Show HN signal: the strongest agentic search products do not replace search results with prose. They teach the agent to operate a real search system.
DeepSeek V4 brings near-frontier coding at a much lower token price. Where cheap reasoning fits in a coding agent stack, from code review to repo mapping.
Flue is trending because it names the part of agent infrastructure that is becoming product-critical: the programmable harness around the model.
jcode is trending because it competes on a less glamorous but important agent metric: how cheap it is to keep many coding sessions alive.
Hugging Face's ml-intern is a domain agent for ML work - papers, datasets, training jobs, and Hub traces. Why domain tools beat generic chat for coding agents.
Open Design turns coding agent CLIs like Claude Code and Codex into a design engine. The real lesson is artifact-first agent wrappers, not design automation.
A trending refusal-direction paper is a reminder that model safety cannot be treated as a thin refusal layer. Builders need layered controls around the model.
Agent skills turn team process into small, reusable operating procedures that load when relevant. Why skills beat one giant prompt for coding agents.
Cloudflare's Agent Memory primitive. What it stores, how ingest and recall work, how it compares to mem0, and how to wire it into your stack.
GPT-5.4 developer guide with OpenAI SDK code, computer use, the 272K-token pricing cliff, and when 5.4 still beats GPT-5.3 and GPT-5.5 in production.
GPT-5.5 and 5.5 Pro for developers: pricing, which tier fits which workload, agentic gains from real evals, a regression to watch, and a migration playbook.
Vercel's agentic infrastructure explained: what the announcement actually names, how AI Gateway, Sandbox, Workflows and Flags compose, with code checked against the SDKs.
Vercel Workflows is GA: durable TypeScript with "use workflow" and "use step". What it means for agents and long-running flows, with code adapted from Vercel's own examples.
Agent runs are opaque. TraceTrail turns a Claude Code JSONL into a public share link with a stepped timeline of messages, tool calls, and tokens.
The second half of our agent tooling release: distribution, validation, and ergonomics layered on top of the first six. Six small CLIs, one through-line.
DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.
Self-healing browser automation harness that lets LLMs complete any browser task. 5,000+ stars in under a week.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.