agent-codemode is an open-source CLI/SDK that lets scripts written by Coding Agents call MCP servers you've already authenticated in Claude Code, Cursor, or Windsurf. Install: npm install -g agent-codemode. It solves the problem of agents burning through context on per-step tool calls by batching them into a single script execution (the author's benchmark shows 99.66% token savings).
ActBench red-teams cowork agents via execution traces, finding ASR of 73.7%–94.4% even when swapping harnesses; Agent Behavioral Contracts II shows co-failure rates hit 90% for same-model two-stage pipelines, breaking the conditional independence assumption; Graph-Based RL Drift Diagnosis uses a small-model recovery graph to detect drift and auto-rollback without retraining the primary agent
Stripe confirms $7B+ acquisition of AI model gateway OpenRouter, expanding into multi-model access and billing; Check Point reveals 11 vulnerabilities across LangChain/LangGraph/CrewAI/AutoGen/MS Agent Framework/Google ADK at Black Hat; Flowise Custom MCP node hit with fourth RCE in a year (CVE-2026-73601); DeepSeek open-sources MIT-licensed DeepSeek Harness; Z.ai releases GLM-5.3 with major coding and cybersecurity benchmark gains; Cursor launches both Builds acceleration and Origin code hosting platform.
headroom compresses tool output, logs, and RAG chunks locally before sending them to the LLM, reaching 66K stars in 7 months. agentmemory gives Claude Code, Cursor, Codex CLI and a dozen other coding agents a shared cross-session memory store, hitting 27K stars in half a year. Andrew Ng's team releases OpenWorker, a desktop agent targeting knowledge workers beyond engineers. NVIDIA's labs-OO-Agents reimagines agent abstractions with object-oriented design. Mastra 1.59.0 renames CostGuardProcessor to TokenCostControl (breaking). browser-use 0.13.8 adds first-party OpenClaw skill support.
Higgsfield closed a $400M Series B led by DST Global, reaching a $5.4B valuation (up over 4x from $1.3B in 8 months). The capital signals that enterprise AI video generation demand is rapidly displacing traditional agency-led production workflows.
Wispr closed a $280M Series B led by Menlo Ventures at a $2B valuation (up ~3x from $700M in November 2025). This round signals VCs betting that voice will replace text input as the next human-computer interface entry point.
Security firm elttam discovered that when Flowise's Custom MCP node runs with CUSTOM_MCP_PROTOCOL=stdio (the default), authenticated users can abuse PYTHONWARNINGS/BROWSER environment variables or exploit the StdioClientTransport's root cwd to bypass existing command and path validation, achieving arbitrary command execution on the host. Rated CVSS v4.0 9.0 Critical, patched in 3.1.3 (CVE-2026-73601). This is the fourth publicly reported RCE against the same Custom MCP feature within one year, highlighting that a 'whitelist commands, blacklist arguments' validation architecture is virtually guaranteed to be bypassed when users can define their own stdio MCP servers. Key mitigations: upgrade, switch CUSTOM_MCP_PROTOCOL to sse, and stop relying on deny-list validation for env/command — an approach that never eliminates the attack surface itself.
Phinq is an open-source runtime governance layer for AI agents. It intercepts every tool call and classifies its risk level — reversible operations pass through, irreversible ones (deletions, payments, credential access, bulk operations) pause for human approval. Install: npx @phinq/phinq. It solves the problem of unsupervised agents making irreversible damage with no trustworthy audit trail.
RippleMem boosts LongMemEval-S accuracy by up to 11.87% via associative memory spreading while cutting graph construction cost to 1/30; Total Recall at What Cost? measures 18–69% prediction error in memory system serving costs with no system winning both cost and accuracy; MESA's dynamic structure selection achieves 8.5% higher accuracy on AMA-Bench while saving 41% of evidence tokens
SpaceX acquires Cursor maker Anysphere for $60B in all-stock deal, gaining GPU cluster access and Grok integration; Stripe acquires model router OpenRouter for $7B+, bridging payments and model selection; Anthropic acquires Israeli startup Decart for ~$60B while Q2 revenue reportedly tops $11.5B; Chinese hackers use AI agent frameworks to breach 85+ Taiwanese government accounts in 4 days; LiteLLM supply chain attack may have hit 2,500+ enterprises
forge adds a reliability middleware layer for tool-calling on self-hosted LLMs, proxying opencode/aider/Claude Code with zero code changes; repo-context-mcp provides token-budgeted repo context packaging via MCP, integrated into PR CI within 5 days of launch; DeepSeek's official harness dsh spawned at least 5 independent community desktop wrappers in one week, totaling nearly 1,500 stars; Microsoft Research's browser agent framework Webwright uses Skill Factory to distill solved tasks into replayable scripts without model calls, boosting reuse accuracy by 15 percentage points on WebArena; Mastra 1.59.0 renames CostGuardProcessor to TokenCostControl (breaking); Pydantic AI v2.30.0 patches a DNS rebinding security vulnerability in its local web chat interface.
AG2 v1.0.2 highlights: (1) AG2 agents can now be exposed as ACP agents, serving remote clients over HTTP/WebSocket; (2) A2A agent cards switch from plaintext to signed-and-verified, plus gRPC TLS transport; (3) LiveAgent adds ElevenLabs as a voice provider, and community extensions (Tenki sandbox, TealTiger governance middleware) land for the first time. No breaking changes.
Muse Glimmer (HF: meta-models/Muse-Glimmer-30B): 29.6B params, 131K+ context, Apache 2.0 fully open-source, zero token cost for local deployment; MCP Atlas 75.5 (vs Gemma4-31B 54.2, Qwen3.6-27B 62.5), SWE-Bench Pro 51.2 leads same tier, but trails Qwen3.6-27B on OSWorld-Verified and TerminalBench 2.1; 4-bit quantized fits under 20GB, DFlash speculative decoding delivers 3.1x speedup on RTX 5090
Claude Sonnet 5 was set to jump from its promo price of $2/$10 to $3/$15 on 9/1. On 8/10 Anthropic updated its pricing page to confirm the increase 'will not happen' — $2/$10 is now the permanent price. For a workload of 300K customer-service conversations per month, that avoids a $1,200/month cost increase (↓33%), and means Sonnet 5 is now permanently cheaper than its predecessor Sonnet 4.6 ($3/$15).
Stealth researchers Hedi Ingber and Aviyam Ivgi found that three major Agent infrastructure platforms (AWS Bedrock AgentCore, Google ADK, Vercel AI SDK) all have dispatch layers that only check whether data looks like a tool call, without verifying it actually came from the model's current inference turn — yielding 4 CVEs (CVE-2026-18830, CVE-2026-18236, CVE-2026-64650/64651). This is not prompt injection — the model was never tricked, because the model was never called. AWS has auto-patched; Google ADK requires upgrading to 2.5.0; Vercel harness packages need upgrading to 1.0.29/1.0.28. The key defense is shifting authorization checks from 'does this data look right' to 'does this correspond to an actual model completion event'.
mcp-memory is an MCP server that persists Agent long-term memory as Markdown files conforming to Google's OKF v0.2 spec, with SQLite FTS5 full-text search indexing. Install: git clone then run `python3 setup.py`. It solves the problem of Agents losing all context on every new session, and memory formats being incompatible across different Agent tools.
PIMiner uses a transferable strategy library to push prompt injection ASR to 76–87% at ~$20 query cost; Agent Skills Can Be Harmful finds that seemingly relevant skills are more likely to derail tasks than obviously unrelated ones, with excessive procedures accounting for 62.6% of efficiency degradation; Order 66 scenario analysis uses a compositional threat model to show that dormant implants, post-hoc memory poisoning, and peer-to-peer diffusion are individually non-fatal but can sustain self-propagation when combined
Vercel ships eve, a filesystem-first TypeScript agent framework tightly coupled with its AI Gateway/Sandboxes; Prime Intellect's Prime Agent treats the entire conversation context as program variables with a self-modifying Continual Harness; aden-hive's Hive replaces pre-compiled execution graphs with 'clone the Queen'; HKUDS's nanobot hits 47k stars in six months with its v0.3.0 Agency Release. No major version bumps on the watchlist today.
Mastra 1.59.0 highlights: (1) CostGuardProcessor renamed and upgraded to TokenCostControl, now supporting user/organization/session tiered budgets with warnAtPercent alerts; (2) Breaking: Factory's autoRunEnabled now defaults to false — rule-suggested executions enter a proposed state pending approval; (3) New listActiveThreadRuns() for low-cost querying of in-progress runs, enabling status-polling UIs.
Vals AI closes a $40M Series A led by Andreessen Horowitz at a $400M valuation. The round signals that VCs are starting to treat 'independent AI evaluation' as essential trust-layer infrastructure for the AI economy — not a nice-to-have leaderboard site.