Know what AI agents can do now.
CapabilityWire tracks new SDKs, MCP servers, model releases, APIs, tools, and libraries, then turns each release into an actionable capability update.
New capabilities, live
- cliClaude Code v2.1.251: PreModelSwitch/PostModelSwitch hooks, subagent tool-call streaming, background session CLIanthropics — an agent can now intercept model switches via PreModelSwitch/PostModelSwitch hooks, stream foreground subagent tool calls to Remote Control clients, and read prompt-cache stats plus spend limits from status line fields.11h ago
- sdkAnthropic Python SDK v1.2.0 promotes files/skills to GA and hardens agent toolsanthropic — An agent can now call Anthropic's files and skills APIs via GA shapes without dated beta headers, upload binary files through Bedrock, and read oversized files by view_range while the memory/agent toolset preserves exact bytes.1d ago
- libraryTransformers v5.16.1 adds GLM-5.3-Flash multimodal MoE supporthuggingface — An agent can now load and run GLM-5.3-Flash (multimodal, 320B/18B-active MoE with hybrid sparse+linear attention) directly via `transformers` for cheaper long-context reasoning, coding, and agentic tasks.2d ago
- libraryvLLM 0.28.0 ships Kimi-K3 + DeepSeek V4 support, DFlash2 spec decoding, tiered KV offload, Rust gRPC frontendvllm-project — an agent can now serve Kimi-K3, DeepSeek V4, and new MoE/multimodal models via vLLM 0.28 with faster speculative decoding (DFlash2, DSpark), tiered KV cache with disk offload, Model Runner V2 E/P/D disaggregation, and a Rust gRPC frontend.2d ago
- frameworkDSPy 3.3.1: managed Python sandbox, GEPA 0.1.4 multi-proposal, MCP v2 structured resultsstanfordnlp — an agent can now run sandboxed Python via a managed Deno/Pyodide runtime with full lifecycle callbacks, use GEPA 0.1.4 multi-proposal optimization, get structured MCP tool results, and rely on adapter default fallbacks for missing output fields.7d ago
- libraryLlamaIndex v0.14.24 adds Claude Sonnet 5 / Opus 5, Gemini 3.7 Flash, GPT-5.6, and multimodal AG-UI inputrun-llama — an agent can now target Claude Sonnet 5 / Opus 5, GPT-5.6, and Gemini 3.7 Flash through LlamaIndex, accept multimodal user input via the AG-UI protocol, and plug in any AsyncDBChatStore as agent memory.9d ago
- protocolModel Context Protocol spec revision 2026-07-28 releasedmodelcontextprotocol — An agent can now negotiate the 2026-07-28 MCP protocol revision with servers, gaining access to any new tool/resource/sampling semantics introduced in this stable release.1mo ago
- sdk@modelcontextprotocol/sdk 1.30.0 released for TypeScriptAnthropic — An agent can now be built or connected via the latest official MCP TypeScript SDK (v1.30.0), picking up the newest transport, tool, and resource APIs from Anthropic.1mo ago
How the feed works
Discover
We scan GitHub releases, PyPI, npm, MCP registries, arXiv, HN, and vendor sources on a recurring schedule.
Classify
The curator extracts what changed, what an agent can do now, package identity, and a minimal example.
Broadcast
One canonical CapabilityEvent, available through MCP, REST, JSON Feed, RSS, and Atom.
Plans for humans and agents.
Buy a subscription on behalf of your agent. Machine-callable checkout is a first-class path — an agent can subscribe by JSON POST.
Free
Enough to prove your agent will actually read the wire.
- ▸Public web + RSS / Atom / JSON
- ▸REST API + MCP
- ▸100 event API + MCP calls / day
- ▸1 named API key
- ▸Per-agent delivery tracking
Agent Pro
A serious allowance for an always-on agent.
- ▸MCP server (streamable HTTP)
- ▸REST API + JSON feed
- ▸RSS + Atom feeds
- ▸10,000 event API + MCP calls / day
- ▸Up to 5 named API keys
- ▸Per-agent delivery tracking
Agent Team
Higher limits and more keys for an agent fleet.
- ▸Everything in Agent Pro
- ▸100,000 event API + MCP calls / day
- ▸Up to 25 named API keys
- ▸Fleet-scale MCP + REST access
- ▸Per-agent delivery tracking
Three ways in.
Point your agent at MCP for tool-shaped access, or hit the REST API from any language.
{
"mcpServers": {
"agentwire": {
"transport": "streamable_http",
"url": "https://api-production-22727.up.railway.app/mcp"
}
}
}curl -s https://api-production-22727.up.railway.app/v1/events?limit=5 \
-H "Authorization: Bearer $AGENTWIRE_KEY"import os, urllib.request, json
req = urllib.request.Request(
"https://api-production-22727.up.railway.app/v1/events?limit=5",
headers={"Authorization": f"Bearer {os.environ['AGENTWIRE_KEY']}"},
)
events = json.loads(urllib.request.urlopen(req).read())["data"]
for e in events:
print(e["kind"], "-", e["title"])