codex

10 articles

← All topics

OpenAI launches Presence — a managed enterprise agent platform with FDE-led deployments and self-reported 75% resolution
openaipresenceenterprise-agentscustomer-servicecodex+5

OpenAI launches Presence, a managed enterprise agent platform with self-reported 75% resolution and 15pp handoff cuts — FDE-led, limited GA, no pricing yet.

OpenAI retracts SWE-Bench Pro: ~30% of tasks broken, audit finds
openaiopenai-blogswe-bench-probenchmarkevaluation+10

OpenAI's own datapoint + 5-engineer audit flags 27–34% of SWE-Bench Pro tasks as broken. It just retracted its own recommendation to use the benchmark.

OpenAI ships GPT-5.6 (Sol, Terra, Luna) and ChatGPT Work
openaigpt-5-6gpt-5-6-solgpt-5-6-terragpt-5-6-luna+9

On 2026-07-09 OpenAI released the three-tier GPT-5.6 family and ChatGPT Work, an agentic product powered by GPT-5.6 with Codex built in and a public system card.

CodeBurn: free, local-first cost tracker for 31 AI coding tools
codeburnai-codingcost-trackingtoken-spendlocal-first+23

CodeBurn (getagentseal/codeburn) reads the session files your AI coding tools already write, breaks down every token and dollar across 31 integrations, MIT, no proxy, no API key.

codebase-memory-mcp: zero-dep code intelligence
codebase-memory-mcpmcpmodel-context-protocoltree-sitterknowledge-graph+12

Pure-C, single-binary MCP server that indexes a codebase into a Tree-Sitter knowledge graph in milliseconds. 13.3k stars, MIT, 5,604 tests, 11 agents. arXiv 2603.27277 reports 83% quality at 10× fewer tokens.

Headroom: open-source token compression for AI agents
headroomai-agentstoken-optimizationcontext-compressionmcp+13

Headroom v0.27.0 is an Apache-2.0 context-compression layer for AI agents: library, proxy, agent wrapper, and MCP server. Published savings reach 92% on code search and SRE debugging.

caveman: terse-output skill, 75k stars in 11 weeks
open-sourcetypescriptclaude-codecodexgemini+21

GitHub JuliusBrussee/caveman: a TypeScript skill for 30+ agent platforms that asks the agent to drop filler. 75k stars, MIT, 65% output-token reduction.

NVIDIA ENPIRE: real-robot coding agents hit 99% pass@8
nvidiacmuuc-berkeleyenpirerobotics+17

NVIDIA GEAR, CMU, and UC Berkeley published ENPIRE, a four-module harness that puts coding agents in a closed loop on real robots. Three frontier agents hit 99% pass@8 on five manipulation tasks.

OpenAI to Acquire Ona: Cloud Runtime for Codex Agents
openaionacodexacquisitionm-and-a+5

OpenAI announces the acquisition of Ona (formerly Gitpod) to give Codex a persistent, customer-controlled runtime for long-running agents. Deal signed, not closed.

ponytail: MIT YAGNI skill cuts AI agent code by 80–94%
ponytailai-agentsyagniclaude-codecodex+11

Dietrich Gebert's ponytail v4.6.0 (2026-06-15): 17.9k stars, 8 releases in 4 days. MIT YAGNI skill for Claude Code, Codex, OpenCode, Cursor, Aider, Kiro. Benchmark: 80–94% less code, 47–77% lower cost.