Three weeks since the [June roundup](/blog/whats-new-spring-2026), and the changelog did not slow down: nine platform releases, [v0.16.2](https://github.com/everruns/everruns/releases/tag/v0.16.2) through [v0.17.7](https://github.com/everruns/everruns/releases/tag/v0.17.7). But the bigger story this time is not a feature list. Everruns stopped being one repository. There are now two more open-source projects in the family — [**Yolop**](/yolop), a terminal coding agent, and [**Mira**](https://github.com/everruns/mira), an evaluation framework — and much of the platform work points at one destination: opening **Everruns Cloud** to the public. Here is the map, then the details. Every platform feature links into the [documentation](https://docs.everruns.com/) or its release notes. ![A release timeline from May 31 to July 11 across three lanes: the Everruns platform shipped nine releases (v0.16.2 to v0.17.7) clustered in the back half of the window; Yolop, newly born, shipped six (v0.1.0 to v0.6.0); and Mira, also new, shipped four (v0.1.0 to v0.4.0). Two of the three projects started within this window.](/blog/whats-new-july-2026-ecosystem.svg) ## Two new projects ### Yolop [Yolop](/yolop) is a new terminal coding agent: one binary that plans, edits, runs, and verifies code in your repository, with persistent sessions, agent skills, MCP servers, and editor integration over the Agent Client Protocol. It is built on the [`everruns-runtime`](https://crates.io/crates/everruns-runtime) we [wrote about embedding in May](/blog/embedding-the-runtime), so its runs are durable and survive a restart out of the box. It stays out of your way. Yolop runs autonomously by default — writes, edits, and commands without a pop-up per action — behind a standing write blocklist, and asks only when a step actually warrants it: **soft approvals** are AI-judged consent points with an audit trail, not a dialog for every file write. (The name is Ukrainian — _йолоп_: a dummy, a fool — describing the attitude, not the results.) Six versions in, it handles multi-language repo maps, native git worktrees, background execution, opt-in LSP-backed code navigation, structural edits via an ast-grep-backed `ast_edit` tool, and authenticated MCP server management. See the [Yolop page](/yolop) or [the source](https://github.com/everruns/yolop). Installing it is one line: ```bash brew install everruns/tap/yolop # or: cargo install yolop --locked ``` ### Mira An agent that cannot be measured regresses silently — a model swap, a prompt tweak, a runtime upgrade, and nobody notices until a user does. [Mira](https://github.com/everruns/mira) (Ukrainian _міра_: measure, standard) is how you catch it: a Rust-first, code-first evaluation framework for multi-turn, tool-using, long-running agent trajectories. You write evals in code — Rust natively, or Python and TypeScript over a documented protocol — and one `mira` host CLI runs them across a model matrix, scores the results, and reports, with saved and resumable runs and CI-native output including a self-contained HTML report. You score more than the final answer. Alongside deterministic checks (`contains`, `regex`, `tool_called`), Mira has trajectory-structure scorers that judge _how_ the agent worked, operational budgets (tokens, cost, latency), combinators, and LLM-as-judge — composed freely into one verdict, so a regression in cost or tool use fails the run as loudly as a wrong answer does. Mira is at [v0.4.0](https://github.com/everruns/mira/releases/tag/v0.4.0); the crate is [`mira-eval`](https://crates.io/crates/mira-eval). ## Everruns Cloud is coming Everruns has been self-hostable open source from day one. The next step is the one people keep asking for: a managed Everruns you don't run yourself. We are preparing to open [**Everruns Cloud**](/cloud) — the same platform we already operate at [app.everruns.com](https://app.everruns.com) — to the public, so you can point an agent at it and go without standing up Postgres, a worker, and a queue. No date to announce yet — [**join the launch list**](/cloud) and we will email you the moment it opens, with occasional progress along the way. ## Sessions that do more ### Real-time session tasks [Session tasks](https://docs.everruns.com/capabilities/task-management/) got the June treatment of webhooks and kept going. Task state transitions now wake a running session mid-turn — on the [durable path](https://docs.everruns.com/explanation/durable-execution/), so a wake survives a crash like everything else — every transition is delivered rather than just the terminal ones, webhook configs are per-task, and structured task results are exposed over both A2A and MCP ([v0.17.7](https://github.com/everruns/everruns/releases/tag/v0.17.7)). An agent waiting on background work no longer polls for it; the work interrupts the agent. ### Forked, detached, and handoff sessions Sessions learned three new tricks. [Forking](https://docs.everruns.com/api/operations/fork_session/) copies a session into an independent branch from any point in the conversation — cheap parallel experimentation on a real history ([v0.17.1](https://github.com/everruns/everruns/releases/tag/v0.17.1)). Detached peer sessions spawn alongside the parent without blocking it, and handoff agents can be invited into an existing session to take over ([v0.17.7](https://github.com/everruns/everruns/releases/tag/v0.17.7)). ### Background subagents [`spawn_subagent`](https://docs.everruns.com/capabilities/sub-agents/) now runs in the background by default, waking the parent on completion ([v0.17.5](https://github.com/everruns/everruns/releases/tag/v0.17.5)). Combined with June's durable subagents, a parent can fan out work, keep going, and pick up results as they land — the same shape as the session-task wakes above, applied to child agents. ### Scoped memory [Memory](https://docs.everruns.com/advanced/memory-model/) stores were org-scoped; they can now be scoped to a single agent or a single user ([v0.17.7](https://github.com/everruns/everruns/releases/tag/v0.17.7)) — an agent's accumulated knowledge and a user's preferences no longer have to share one org-wide pool. ## Evals and trajectories ### Observers June's online judges grew a face. Observers — the machinery that scores live sessions — now have their own UI: create and edit them against a scorer catalog, review results in a per-observer Quality tab, and `llm_judge` scorers that reference a model your org cannot use are rejected up front instead of failing at runtime ([v0.17.2](https://github.com/everruns/everruns/releases/tag/v0.17.2)). ### Eval runs: compare, share, import Three quality-of-life pieces for [evals](https://docs.everruns.com/features/evals/): side-by-side run comparison with regression highlighting ([v0.17.4](https://github.com/everruns/everruns/releases/tag/v0.17.4)), read-only revocable share links for runs ([v0.17.5](https://github.com/everruns/everruns/releases/tag/v0.17.5)), and ingestion of externally-executed runs with full attribution, transcript, and matrix views ([v0.17.2](https://github.com/everruns/everruns/releases/tag/v0.17.2)). That last one is the Mira bridge: run an eval anywhere, view it in the platform. ### ATIF across the stack One thread ties all three projects together this cycle: the [Agent Trajectory Interchange Format](https://github.com/harbor-framework/harbor/blob/main/rfcs/0001-trajectory-format.md). The platform exports sessions and eval datasets to ATIF, segmented for large sessions ([v0.17.6](https://github.com/everruns/everruns/releases/tag/v0.17.6)); Yolop writes ATIF trajectory files with `--trajectory-out`; Mira exports saved runs to ATIF with `mira export --format atif`, verdicts stamped in. One format for what an agent actually did — ready for fine-tuning, RL, or trajectory-visualization tooling, whichever project produced it. ![A diagram of features shipped since the June roundup, grouped into four themed cards: New projects (Yolop, Mira), Everruns Cloud is coming (managed Everruns opening up, join the launch list), Sessions that do more (real-time task wakes, fork / detach / handoff, background subagents, scoped memory), and Evals and trajectories (Observers UI, compare / share / import runs, ATIF export).](/blog/whats-new-july-2026-feature-map.svg) ## Also since June Smaller changes worth knowing about: - **MCP, always.** The [MCP endpoint](https://docs.everruns.com/features/mcp/) is now always exposed — the feature flag is gone ([v0.16.2](https://github.com/everruns/everruns/releases/tag/v0.16.2)) — and it conforms to the 2026-07-28 stateless MCP spec ([v0.17.1](https://github.com/everruns/everruns/releases/tag/v0.17.1)). - **Parallel tool calls.** A [`parallel_tool_calls`](https://docs.everruns.com/capabilities/parallel-tool-calls/) preference, unified across all LLM drivers ([v0.16.2](https://github.com/everruns/everruns/releases/tag/v0.16.2)). - **Providers and models.** Typed multi-field credential schemas make OAuth a first-class way to connect a provider, starting with [OpenRouter](https://docs.everruns.com/providers/openrouter/) from the Add Provider dialog. New model profiles: [Claude Sonnet 5](https://docs.everruns.com/providers/anthropic/) and [GPT-5.6](https://docs.everruns.com/providers/openai/) Sol, Terra, and Luna. - **Streaming reconnect.** LLM streaming responses reconnect automatically on transport failure ([v0.17.6](https://github.com/everruns/everruns/releases/tag/v0.17.6)) — one less way for an hours-long run to die. - **UI polish.** A unified five-zone layout across the main pages, a combined model-and-effort composer menu with recents, an LLM speed selector mapped to OpenAI's `service_tier`, and keyboard turn navigation for chat transcripts. --- All of it is open source, MIT-licensed: [everruns/everruns](https://github.com/everruns/everruns), [everruns/yolop](https://github.com/everruns/yolop), [everruns/mira](https://github.com/everruns/mira). The reference is at [docs.everruns.com](https://docs.everruns.com/). And if a managed Everruns is the thing you have been waiting for — [contact@everruns.com](mailto:contact@everruns.com), we would like to hear what you plan to run on it.