Semble: Fast and Accurate Code Search for Agents

Fast regex search: indexing text for agent tools · Cursor

How we're building indexes for regular expression search so agents can find text in large monorepos without the 15-second ripgrep waits.

DataLicenses.org

Machine-readable hints for AI agents/crawlers; easy to adopt, rely on compliance.

Meilisearch: Unified Search & AI Retrieval Platform

Build lightning-fast search and AI retrieval with Meilisearch. Open-source, developer-friendly search engine trusted by 20,000+ teams worldwide.

Memory retrieval tuned to your knowledge base | Enzyme

Your users bring content. Enzyme gives your agent their conceptual landscape from the first import. 42,000+ installs. Local CLI and hosted memory workflows.

Cognition | Agent Trace: Capturing the Context Graph of Code

We’re excited to join in Cursor, Cloudflare, Vercel, git-ai, OpenCode and others in support of [Agent Trace](https://agent-trace.dev/). As described in the spec, Agent Trace is an open, vendor-neutral spec for recording AI contributions alongside human authorship in version-controlled codebases.

AI Coding Agent Benchmarks & Leaderboard | Artificial Analysis

We measure real-world performance of coding agents on software engineering tasks, including cost, token usage, and execution time. We compare how performance changes across agents, models, and execution settings.

Open Coding Agents: Fast, accessible coding agents that adapt to any repo | Ai2

SERA is the first in our family of Open Coding Agents, achieving state-of-the-art performance at low cost.

Agentic Engineering Patterns - Simon Willison's Weblog

Patterns for getting the best results out of coding agents like Claude Code and OpenAI Codex. See my introduction for more on this project.

Agent Trace

A standard format for tracking AI-generated code.

OpenCode Zen | A curated set of reliable optimized models for coding agents

OpenCode - The open source coding agent.

Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study

As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Large Language Model (LLM) agents have been widely adopted in modern software development workflows. SWE-bench [13] and related works [23, 24, 22, 25, 15] establish the task of issue resolution as a de-facto standard for assessing their capability and usefulness. In this setting, an agent is given an entire codebase, a task description (e.g., a bug report or feature request) in natural language and is instructed to produce a code patch that resolves the issue and passes the repository’s test suite. These benchmarks have been instrumental in demonstrating both the substantial potential and the persistent limitations of current models as SWE agents.