How fast invergent-ai/surogates is gaining stars, and where it lands on Trendshift and GitHub Trending
Activity and trending
Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending
Nov 11 – Nov 19, 2026
Stars +0in 9 days
01
Forks +0in 9 days
01
Merged PRs 65in 9 days
0102030
26
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Nov 11Nov 13Nov 15Nov 17Nov 19
The left and right arrow keys step from day to day; Home and End go to the first and the last
Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day
Stars gained
Forks gained
Merged PRs
Wed, Nov 11, 2026
+0
+0
26
Thu, Nov 12, 2026
+0
+0
23
Fri, Nov 13, 2026
+0
+0
6
Sat, Nov 14, 2026
+0
+0
0
Sun, Nov 15, 2026
+0
+0
1
Mon, Nov 16, 2026
+0
+0
4
Tue, Nov 17, 2026
+0
+0
1
Wed, Nov 18, 2026
+0
+0
4
Thu, Nov 19, 2026
+0
+0
0
Total
+0
+0
65
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
One human "yes" should approve one tool call, not the tool. In Surogates, approving a gated tool mints a grant for that exact call: - keyed on a SHA-256 of its arguments, so "deploy prod" doesn't…
Listing tools: in a skill doesn't gate it. requires_tools: does. In Surogates, tools: on a regular skill is author metadata. The runtime doesn't read it. Only experts use it, to scope their own tool…
Setting your agent's egress to "deny" doesn't cut its network. In Surogates, egress rules check the URLs of 4 tools only: web_search, web_extract, web_crawl, browser_navigate. Still open: • terminal…
Before you fine-tune on your agent's logs, throw out the runs that went wrong. Logs are a cheap dataset for a small task model: real requests, real tool calls, real answers. They also keep every…
Your agent just saved a new memory. Don't put it in the system prompt yet. Prompt caching reuses work only while the start of the prompt stays the same. The system prompt comes before the whole chat.…
OpenRouter for agents and sandbox environments. Provides a control plane and configuration options for persistent agent workers. Route runtime + substrates, provision specialist presets, and supervise your fleet.
OpenMA handles sessions, execution and recovery, so you can build and run agents with any model, any harness, any sandbox, on any cloud. An open-source, self-hostable alternative to Claude Managed Agents and OpenAI Agents API.
a13n - Build, run, and manage AI agents at scale on your own infrastructure. Open source, with a built-in harness, durable execution, multi-provider support, and a management console. Built With Love 💜 @converge-ai-labs
Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.