Mistral Vibe (Remote Agents) + Mistral Medium 3.5

https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5

Vibe is Mistral's cloud-hosted coding-agent platform: each session runs in an isolated sandbox with task state, history, and approvals. Spawnable from CLI or Le Chat, with parallel execution. Local CLI sessions can be "teleported" to the cloud and resumed. Powered by Mistral Medium 3.5 (77.6% SWE-Bench Verified). Plugs into GitHub, Linear/Jira, Sentry, Slack/Teams.

Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 74 cited facts, 11 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Latest release
mistral-vibe v3.0.1 (2026-10-20) registry fix
Freshness
2026-10-23 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
both vendor fix
Maturity
preview vendor fix
SDK languages
python, rest, typescript vendor fix
Protocols
mcp-client repo fix

Memory taxonomy

storage
kv
retrieval
injection
persistence
cross-session
update
append-only
unit
episode
governance
opaque
conflict
none

When to use

Optimised for: async parallel coding agents with teleportable session state; SWE-Bench-leading model (77.6%); EU-jurisdiction stack

Anti-fit: not for non-Mistral stacks; not for users requiring full transparency of memory eviction policy; not for offline/air-gapped use

Pros & cons

Pros

Async parallel coding agents with teleportable session state; broad ecosystem integrations (GitHub/Linear/Jira/Sentry); SWE-Bench-leading model; weights open; EU-jurisdiction stack.

Cons

Vibe service closed; SWE-Bench claim is vendor self-report; no third-party reproduction yet; pricing tied to Pro/Team/Enterprise tiers; opaque memory eviction policy.

Claims & capabilities

Mistral Medium 3.5: 77.6% SWE-Bench Verified; 91.4 on τ³-Telecom (agentic)

Technical surface

API surface
REST + CLI (Mistral CLI) + Le Chat web; SDK Python/JS
Backend storage
custom (Mistral-managed sandboxes)
Deployment
Managed cloud (la Plateforme + Le Chat) + NVIDIA NIM containers
Embedding model
Mistral embed-v2 (default; multiple supported)
Multi-tenancy
hard-isolation (per-session sandbox)
MCP
native (first-party — Mistral Agents support MCP)
A2A
searched not found
OpenTelemetry
searched not found

Compare Mistral Vibe (Remote Agents) + Mistral Medium 3.5 with…

Similar systems

Other coding-agent memory in the catalog, ranked by inbound references.

  • Devin (Cognition) T1

    Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads past session trajectories for self-improvement; writes notes for recurring scheduled tasks.

  • Aider T2

    Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries static preferences.

  • Augment Code T1

    Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. MCP endpoint exposes the graph. Acquired by Harness (2026-10-08): Harness bought select Augment Code assets, including Cosmos, the Auggie CLI and the Context Engine, and the team joined Harness. augmentcode.com now leads with Cosmos, a software-factory agent platform.

  • Letta Code T3

    Letta's stateful coding-agent harness: agents rewrite their own memory blocks and skills, version context in git via MemFS (syncable to GitHub) and reflect via a periodic /sleeptime 'dreaming' process. from Letta (MemGPT) team. letta-ai/letta-code is now the main Letta source (harness, terminal UI, App Server, channels); the Letta V1 API server was retired to the archive branch of letta-ai/letta.

  • Replit Agent T1

    No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory relies on filesystem + agent-written notes.

  • agentmemory (rohitg00) T3

    Self-hosted persistent memory layer that captures coding-agent activity and recalls it in later sessions, positioned on public benchmark results. #7 in TeleAI Awesome-Agent-Memory

Sources (73 cited facts, 11 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-22
    • License “Modified MIT (Medium 3.5 weights); Vibe service closed” → “Apache-2.0 (Vibe CLI); Modified MIT (Medium 3.5 weights)” source
    • Latest release “Medium 3.5 weights on Hugging Face (modified MIT); Vibe service closed” → “mistral-vibe v3.0.1 (2026-10-20)” source
    #195

Related systems

References (1)

  • Mistral Large 2 / Mixtral family depends on at runtime — adjacent-infrastructure cell: requires Mistral la Plateforme + Le Chat; integrates GitHub/Linear/Jira/Sentry/Slack/Teams; NVIDIA NIM containers for self-host