Firekeep

Firekeep

Your agents shouldn’t work like strangers.

Connect Claude Code, Codex, Kiro, OpenCode, and other MCP clients through one shared, self-hosted Keep.

Every solved problem should make the next one easier. Firekeep preserves the experience behind the work — durable knowledge, working state, procedures, coordination, and inspectable evidence — and puts it back to work in the next session, tool, or machine.

Use it for your own continuity on one workstation. Add teammates when you need them without starting the team’s context over.

Website · Install · Product tour · Firekeep Studio · Evidence · Privacy · Support

One Keep, across runtimes

flowchart LR    A["Claude Code<br/>stores a proven fix"] --> K[("your self-hosted<br/>Keep")]    K --> B["Codex<br/>recalls the fix + evidence"]    K --> C["Kiro<br/>reuses the procedure"]    K --> D["OpenCode / MCP client<br/>continues informed"]

Agents keep their native interfaces and provider-owned sessions. What carries forward is the Firekeep context they explicitly record and recall through the same local MCP gateway. That means one person can switch tools without losing the thread, and a team can earn context once and carry it forward.

See Claude Code and Codex share one Keep →

Install Firekeep

The installer configures Claude Code, Codex, Kiro, and OpenCode together (plus Claude Desktop when its config directory exists), then asks where your Firekeep server should live. The full setup flow is in the install guide.

curl -fsSL 'https://firekeep.ai/latest/install?src=github' | sh    # macOS / Linuxirm 'https://firekeep.ai/latest/install.ps1?src=github' | iex      # Windows PowerShell

The server runs on linux/amd64 or linux/arm64 (server releases after v1.6.2; v1.6.2 and earlier are amd64-only) and needs Docker Compose v2, two CPU cores, and Git; 16 GB RAM is recommended for the default stack. It binds to 127.0.0.1 by default. See the requirements and sizing notes before choosing a host.

Trying Firekeep for the first time? Share what worked and where you got stuck →

Runtime coverage

• Client Kit: configures Claude Code, Codex, Kiro, and OpenCode together; Claude Desktop is added when its config directory exists. Other MCP clients can use the generic path.
• Claude Code: managed MCP, instructions, and lifecycle hooks. Its supported pre-tool hook can hard-block an edit, write, or shell action.
• Codex: managed MCP plus AGENTS.md guidance. Codex exposes no native hooks, so lifecycle automation and pre-edit enforcement are not implied.
• Kiro CLI: a named Firekeep agent with MCP, steering, and lifecycle hooks. On the validated Kiro CLI 2.12.1 surface, its pre-edit hook is advisory.
• Firekeep Studio: runs Codex, Claude Code, Kiro CLI, and Grok in one desktop workspace. The direct Grok adapter has no Keep memory, hooks, or briefing; Studio reports that boundary instead of inheriting another runtime’s status.

See the integration guide and Studio runtime matrix for the maintained details.

Measured retrieval, with the method attached

On the accepted 2026-08-28 LongMemEval-S run, Firekeep achieved 97.7% Evidence Recall@10: at least one labeled evidence session appeared in the first ten results for 459 of 470 scored questions. The measurement covers retrieval, not generated-answer accuracy; it is one corrected deterministic run rather than a multi-run confidence interval.

Methodology · Result data

The problem Firekeep solves

People do not build professional judgment by rereading every email, document, ticket, or source file from the beginning. They remember what happened, why a decision worked, how a failure was diagnosed, and which procedure held up in practice. That experience changes how they approach the next problem.

Agents should improve the same way. Firekeep connects the knowledge, working state, coordination, and evidence behind the work so the next agent can begin with the experience the last one earned.

Detailed capability map

Why Firekeep Is Different

Firekeep is not another chatbot wrapper or prompt orchestration layer.

It is an operating layer for connected AI agents — infrastructure that sits behind your existing tools and makes them better.

• Self-hosted by default. The server, datastores, embeddings, and default generation model run on your infrastructure. Third-party egress occurs only when you opt into a connector or external Symdex AI provider.
• Deep where the work happens. Coding is the strongest shipped workflow, with Symdex for code intelligence. It is not the product boundary: Docdex brings selected document folders into the same Keep, Maildex brings a member's email (read-only IMAP, always member-private, firekeep maildex add), and the shared continuity, coordination, governance, and evidence layers are domain-independent.
• Persistence + observability. Most agent tools focus on making the agent smarter in the moment. Firekeep focuses on what happens between sessions and after things go wrong.
• MCP-native. Four remote services and two client-local backends expose Model Context Protocol tools through one local firekeep stdio gateway. Shipped adapters configure Claude Code, Claude Desktop, Codex, Kiro, and OpenCode; other MCP clients can be configured manually.
• Agent-agnostic. Swap the agent client without rebuilding the underlying memory and coordination layer. Cursor has a documented manual MCP path; Aider does not currently have a shipped adapter.
• A2A-discoverable. Relay publishes an Agent-to-Agent agent card at /.well-known/agent.json for capability discovery. This is discovery-only, not an A2A task-execution endpoint.

Installation and operations details

One command, two required questions: the agent identity every memory, session and replay event is attributed to, and where your Firekeep server is — set one up on this machine with Docker, redeem a join code, point at one that is already running, or decide later (firekeep doctor then tells you how to finish). Setting one up here runs firekeep init for you; that installer asks nothing, and the machine enrols itself once the stack is up, so firekeep doctor is green with no dashboard, no tunnel, and no pasted key. It prints the paste-ready command for your second machine when it finishes.

The installer then offers one skippable prompt for another MCP client's rules file; the four shipped adapters are rendered either way.

Server images after v1.6.2 are published for linux/amd64 and linux/arm64, so an x86-64 or ARM64 Linux host (e.g. AWS Graviton, Ampere) or Docker Desktop on an Apple-silicon Mac runs them natively; v1.6.2 and earlier are amd64-only. The client bootstrap is exercised in CI on Ubuntu, Debian, Alpine, Fedora, Rocky, Arch and openSUSE (x86_64 and aarch64); macOS runs the same script but is not covered by CI.

• Requirements and sizing — firekeep.ai/docs.html#requirements
• Server install — firekeep.ai/docs.html#server
• Connecting agents and teammates — firekeep.ai/docs.html#connect
• Troubleshooting — firekeep.ai/docs.html#troubleshooting

From this checkout

bash install.sh              # build the server from sourcebash install.sh --pull       # the same installer against the published imagescd client && ./install       # the kit from this checkout (.\install.ps1 on Windows)firekeep install             # re-render the runtime adapters only

install.sh prompts for nothing: the host address is detected and the Neo4j password generated (--ip / --neo4j-password, or FIREKEEP_VPS_IP / FIREKEEP_NEO4J_PASSWORD, override either). It returns as soon as the stack is up rather than blocking on the ~3.3 GB model pull — until that finishes, memory writes return status="partial" (stored and queued for backfill, not yet searchable) and firekeep doctor carries an embeddings WARN row saying so. bash install.sh --wait-for-models blocks instead.

Operating the server afterwards — access and authentication, the dashboard, backups, updates, exposing ports deliberately — is docs/DEPLOYMENT.md.

Removing it

firekeep uninstall            # remove the client kit from this machinefirekeep uninstall --server   # also tear down the server + ALL its data

firekeep uninstall removes only what the kit installed — the Firekeep blocks in each runtime's config (your own settings stay intact), the launcher and its PATH entry, and ~/.firekeep — and asks first (--yes skips the prompt). It never touches a server you set up. --server additionally runs docker compose down -v on the stack this machine provisioned, deleting the Neo4j/Qdrant/Redis volumes — every memory, session and secret, permanently — behind a separate data-loss confirmation that a plain uninstall or --yes can never trigger. Back up first (docs/DEPLOYMENT.md) if you might want the data back.

Firekeep Studio

[Firekeep Studio showing a multi-runtime conversation workspace, sessions, Mission controls, and runtime status]

Download for Windows · Download universal macOS · Explore Studio →

studio/ is a separate desktop client for people who want Firekeep to be the only agent application they open. It gives Codex, Claude Code, Kiro CLI, and Grok one runtime-neutral conversation surface: any supported runtime can be the explicit primary, other runtimes can review it in fresh read-only contexts, and /compare, /consensus, an explicit shared workspace, Windows voice input and system voice output, cache-aware token guards, named and color-coded local sessions, live provider model/reasoning discovery, and typed Client Kit controls are built in. The selected runtime is visually explicit, the full inspector can be hidden, and Studio links to the dashboard from the existing Client Kit connection without exposing its credentials. Fenced Mermaid responses render as native zoomable diagrams, and the existing Firekeep Decision Board opens as a native question/evidence/action panel inside Studio. Its local authenticated push preserves the original long poll, avoiding an extra agent turn merely to discover that the board is ready. The primary runtime picker shows live readiness and transport context, response scrolling respects readers who move away from the tail, and copy/paste uses bounded text-only native clipboard operations. Completed answers lead each run while detailed working events fold into a Work log. A runtime-neutral Agents view tiles Codex, Claude, Kiro, Grok, or any future chat-capable adapter into selectable panes with independent native continuations; the shared composer targets the selected pane, and active runs remain serialized for workspace safety. Mission Mode adds an outcome-bounded harness: one primary writer, deterministic local checks, bounded repair, independent review evidence, explicit human acceptance, and a task result stored separately from every agent's prose.

Studio consumes provider-supported structured boundaries rather than scraping TUIs, keeps provider authentication provider-owned (except OS-encrypted API keys), and continues to use the existing Python Client Kit wherever a runtime's native configuration provides Keep memory, hooks, policy, and connectivity. Runtime cards report that evidence explicitly; the direct xAI Grok adapter is clearly marked as having no Keep memory rather than inheriting another runtime's claim. The preview build and installer commands, security boundaries, runtime matrix, and full / command inventory are in the Studio README.

Studio 0.5 ships an x64 Windows installer and a universal macOS installer from an isolated, signed release channel. Packaged builds check for Studio updates shortly after launch; Windows downloads and installs a verified update on restart, while macOS uses native automatic updates only when the release is Apple-signed and notarized. The current release page, checksums, and both installers are published under Firekeep Studio releases.

A Real Workflow

Here's what happens when an agent uses Firekeep:

1. Session starts. On runtimes with lifecycle hooks, the client fetches Cortex's aggregated GET /briefing first, including relevant memories, tasks, environment state, and skills. The agent then calls ctx_start_session("fix auth middleware bug"); Bridge creates the durable session and the shim ties it to that briefing.

2. Code exploration. Instead of reading every file, the agent calls search_symbols("auth middleware") and get_callers("require_scope") on Symdex. It gets a targeted list of files and callers in milliseconds.

3. Environment check. Sentinel has been watching Docker. It detected that the cortex-api container restarted 3 times in the last hour and pushed an alert to Relay's #alerts channel. The agent sees this in its context.

4. Work happens. The agent edits files, runs tests, and records important progress with ctx_update. Bridge persists what was explicitly recorded. When the context window compresses, the agent calls ctx_get_shadow and gets that durable working state back — plans, decisions, progress, and file knowledge.

5. Session completes. The agent calls ctx_complete_session, optionally passing a structured self-grade — task_result ("success" / "partial" / "failure", the TASK's outcome, not the RPC's) plus up to 10 short task_evidence claims backing it. The grade is accepted only from the session's verified owner and stored as that session's one authoritative, never-overwritten result. Bridge atomically marks the session complete and queues background distillation into episodic memory; failures retry and eventually move to a visible dead-letter queue. Auto-evals compute quality metrics from the replay trace — a session with no recognized grade reads as unknown rather than a guessed success, so outcome-driven scoring (Outcome-Weighted Memory, quality trends) never counts silence as a win. Next time someone works on auth middleware, the memories are there once distillation succeeds.

6. Something went wrong? Open the Replay tab in the dashboard. Load the session. See every action, every memory read, every decision point. Click on a failure event and run narrowing — it walks back through the causal chain to help identify the root cause.

Architecture

Local Machine                               VPS┌──────────────────────────┐              ┌────────────────────────────────────┐│ Claude / Codex / Kiro /  │              │ FirekeepCortex   — Memory & RAG    ││ OpenCode / MCP client    │              │ FirekeepBridge   — Sessions        ││           │              │              │ FirekeepSentinel — Monitoring      ││  one `firekeep` gateway  │◄──── MCP ───►│ FirekeepRelay    — Coordination    ││    ├─ symdex (local)     │              │ Dashboard        — Web UI          ││    └─ decision (local)   │── Browser ──►│ Neo4j · Qdrant · Redis · Ollama    │└──────────────────────────┘              └────────────────────────────────────┘

Symdex and the Decision Board run client-side as stdio-local MCP servers (installed with the kit) — Symdex must be local to the working tree it indexes, so it is no longer a VPS container.

The two arrows crossing that boundary are not publicly reachable by default. Out of the box the VPS side listens on loopback and requires an API key, so the local-machine half reaches it over an SSH tunnel, a private network, or an HTTPS front end you deliberately configure. See docs/DEPLOYMENT.md → Access and authentication.

Code intelligence (FirekeepSymdex — 38 MCP tools, 8 analytics hidden behind a flag) and the Decision Board (firekeep-decision) run client-side as stdio-local MCP servers installed with the kit, not as VPS containers.

Shared modules (no extra containers): Replay Engine (structured trace log across all services), Auth (API key scopes), Vault (Fernet-encrypted secret storage), Corpus (business document ingestion → vector chunks; scheduled Confluence collectors), Auto-Evals (10 Tier-1 quality metrics + trend tracking + regression detection), Pattern Engine (strategy detection; promotion validation and A/B experiments are feature-flagged off by default), Policy Engine (compound pre-edit safety checks — lease, file risk, path deny, session health, recent failure), Agent Gateway (predict-then-act surface with fast-path cache for repeated low-risk actions), Skills (agent-authored via skill_create + docs→skills drafts under human review; server-side synthesis off by default), Memory Improvements (archive-first composite aging with preview/audit/restore, token budgets, LLM synthesis pass, embed input capped + shrink-to-fit).

For the full design specification, see docs/DESIGN.md.

Dashboard

Access at http://localhost:8040 on the host, or through a tunnel from elsewhere (docs/DEPLOYMENT.md → Reaching the dashboard). It has its own basic-auth login (user admin; the password is written once to dashboard/.htpasswd.cred). Behind that, nginx injects the dashboard's API key on every backend call, so the SPA works against the auth-gated stack without you pasting a key into the browser.

The dashboard is a zero-dependency static SPA. No build step, no npm, no framework.

Documentation

Tech Stack

Python 3.11 server services (client supports Python 3.10+) / FastAPI / FastMCP / Neo4j / Qdrant / Redis / Ollama / Docker Compose / tree-sitter / TypeScript / Electron / React

Server-side embeddings and generation default to local Ollama, so the default server path has no model API bill. Symdex can optionally use Anthropic, Gemini, or an OpenAI-compatible endpoint for symbol summaries and scaffolding; enabling one of those providers may send code snippets off-machine and incur provider costs. Background auto-indexing explicitly disables AI summaries.

Roadmap

Working now

• Full memory lifecycle (learn, recall, decay, contradiction detection, versioning)
• Four memory types (reference / procedural / episodic / transient) with type-aware recall decay; direct learns default to episodic while raw event consolidation classifies extracted knowledge
• Token-conscious recall with optional LLM synthesis
• Archive-first composite aging (age × access × confidence) with dashboard preview, audit and restore; confirmed memories, skills and corpus chunks are never age-archived, and automatic hard purge is off by default
• Team continuity: verified workspace/member provenance plus runtime agent_id + project, contributor reports, LLM-synthesized handoff briefs
• Session persistence through context compressions, with crash detection and workspace-snapshot resumption
• Bridge replay emission on session lifecycle (started / updated / completed / abandoned)
• Docker + git + file monitoring with Relay alerting; container/commit/file activity flows to the replay stream
• Agent coordination: channels, bulletin board, fencing-token leases, structured task queue, presence registry, direct messages
• Pre-flight briefing assembles intelligence from all services at session start; surfaces discipline warnings when memory calls arrive without identity headers
• Session debrief: guided completion with task updates and lease cleanup
• Multi-agent support (task assignment, inbox polling, file lease enforcement)
• Skills: agent-authored via skill_create (client-side) + a docs→skills pipeline (paste / URL / scheduled Confluence collectors) drafting skills under human review; top matches injected into the next briefing (server-side auto-synthesis exists behind SKILL_SYNTHESIS_ENABLED, off by default)
• Night Shift: firekeep night-shift drains the fleet job catalog — session distillation (queued by the session-end hook), stale-skill re-authoring and contested-verdict proposals (queued nightly by the server) — on your own machine against a local model (LM Studio or Ollama, auto-detected), writing memories attributed to the original session, draft skills that name the stale skill they rewrite (reauthor_of), and verdict proposals recorded on the contested pair — never applied, always waiting for a human. Session start spawns it in the background when a local model port answers (FIREKEEP_NO_AUTO_NIGHTSHIFT=1 to opt out). Generation stays off the server; cloud-hosted models are refused by default so session content cannot leave the machine
• Decision Board: agent-spawned local clarification board pre-populated with retrieved team-memory evidence (firekeep-decision stdio server + Cortex /decision/synthesize)
• Personal / bypass mode: in-session /personal (or firekeep personal / FIREKEEP_BYPASS=1) makes Firekeep fully dormant for private work — hooks, sidecar, decision board, and shim all honor one is_bypassed() gate; auto-clears at session end
• Pattern Engine: strategy detection, category classification (procedural / risk / behavioral), and quarantine controls; automated promotion/validation is implemented behind PATTERN_VALIDATION_ENABLED=false by default
• Experiment framework: named datasets, chi-square significance tests, effect-size confidence intervals, and controlled strategy-tip experiments behind PATTERN_EXPERIMENTS_ENABLED=false by default
• Optional feedback loop for measuring whether briefing tips improve outcomes when pattern validation is enabled
• Runtime policy engine: compound pre-edit checks (lease, file risk, path deny, session health, recent failure)
• Agent Gateway (predict-then-act): MCP action_before / action_after, gateway returns allow | rethink | block, fast-path cache for repeated low-risk actions
• Encrypted secrets vault (Fernet) with MCP tools and REST API
• Replay traces with root-cause narrowing and per-event context reconstruction
• Auto-evals: 10 Tier-1 quality metrics computed on session completion, trend tracking, regression detection
• Knowledge Autopilot round 1 (visibility, never autonomous mutation): feedback-weighted recall + the memory_feedback tool, a Bridge session reaper so crashed sessions count as failures, contested-not-superseded handling for unconfirmed memory conflicts with human verdicts, the Autopilot review inbox + weekly digest, a per-memory evidence ledger (/memory/{id}/evidence), and a shadow-mode skill ladder that records which drafts would earn trial and which trials would earn active — see docs/guides/knowledge-autopilot.md
• Living Instructions rounds 1 + 2 (measurement): the per-instruction compliance table on the Autopilot tab (predicates frozen to a pre-registered baseline), trend over time, and the round-2 measurement contract — instruction-content hashes stamped into the rendered block, five attribution headers, per-runtime slices, and exposed/not-exposed/unknown states with everything unverifiable reported as unknown. Rewrites under human verdict and briefing-delivered A/B variants are roadmap — see the design spec in docs/ROADMAP.md
• Dreaming: automated memory consolidation + person profiles (DREAM_ENABLED, off by default)
• Living Procedures rounds 1 + 2: skills observed as procedures with frequency/efficacy proposals under human review, and — round 2 — Enforced Runbooks: command-step matchers, human-armed advise/require_ack/block enforcement with success-gated evidence, a challenge→ack→one-use-permit protocol, fail-closed block mode, and a per-workspace deviation ledger surfaced on the dashboard and in the Autopilot inbox (PROCEDURE_ENABLED, off by default; dogfooding before any announcement) — see docs/guides/living-procedures.md
• Trust Ledger round 1: a per-agent employment record aggregated on demand from replay gateway events (GET /autopilot/trust + a dashboard card) — declared/reconciled counts, prediction-match calibration, reversals, sessions. Visibility only, deployment-global, frozen formulas pre-registered before the first published number. The enforcing capability broker (earned autonomy) is a later round
• Corpus tenancy hardening: member-private document sources with a shared visibility filter at every egress, source-scoped point identity (identical text across members no longer collapses to one deletable point), principal-aware source authorization, and a committed-generation gate — general infrastructure beneath the forthcoming client dexes
• One degrading local MCP gateway registered by every adapter, aggregating four remote services plus the client-local Decision Board and whichever dexes are registered
• The dex registry: dexes are the domain indexes the Keep understands, listed and switched with firekeep dex list|add|remove against ~/.firekeep/dexes.json. All three wheels ship bundled and checksum-verified with every release — registration gates activity, not installation. Symdex and docdex are registered by default (since client 1.2.0 an absent registry is seeded with both); firekeep dex remove is the off-switch, and removals stick across updates. The same file also carries capabilities — entries that operate a domain rather than index it, marked role: capability, neither bundled nor ever seeded — see docs/guides/dexes.md
• Code intelligence: client-side firekeep-symdex behind the gateway (38 tools, 8 analytics hidden behind a flag), mounted when registered as a dex
• Documents: client-side firekeep-docdex — folders a human registers (firekeep docdex add ~/Notes) extracted to text and ingested into the corpus, surfacing through ordinary memory_recall. Private to the member by default even on a shared Keep, --shared for the workspace; md/txt/pdf/docx, no OCR; deletion of a local file removes its corpus replica on the next sync
• Email: client-side firekeep-maildex — IMAP mailboxes a member registers (firekeep maildex add), read-only (every open is EXAMINE, every fetch PEEK; no send capability in the wheel), always member-private
• Desktop: client-side firekeep-hands — the registry's first capability rather than an index, so it operates its domain instead of indexing it. Your runtime observes and drives this computer's apps and a Hands-managed browser, and every consequential step waits for a separate approval broker that accepts only a real, non-injected keystroke. Opt-in and never bundled (firekeep hands enable), never seeded; the honest limits — locked screens, elevated windows, screenshots leaving the machine, prompt injection — are stated in docs/guides/hands.md
• Docs→skills knowledge pipeline (knowledge_ingest, URL ingest) + opt-in scheduled Confluence collectors (SP3)
• Web dashboard with Devices and Members management alongside memory, coordination, replay, policy, and operations
• A2A agent card endpoint (/.well-known/agent.json) for external discovery
• Business knowledge ingestion: chunk documents into vector store, surface during memory recall
• Webhook notifications (Slack, Discord, generic HTTP)
• Authentication: per-key API scopes (memory:read/write, session:read/write, replay:read, eval:read, admin, …), on by default, with keys bootstrapped by the installer

Promised (the two roadmap rungs published on firekeep.ai)

• Linked instances — multiple Firekeep servers sharing knowledge across an organisation, so what one team learns is recallable by another
• Domain profiles — separate experiences (coding and documents today; research ahead) as profiles of the same client kit over one shared brain: never separate products, never separate memory stores

The decision record behind both — profiles-not-clients, the linkage-layer prerequisite, outcome-signal gating, sequencing — is docs/ROADMAP.md.

Planned (smaller)

• Grafana metrics export
• Jira connector ingestion (wiki/Confluence auto-sync already shipped, opt-in)
• Skill versioning and rollback

Status

Firekeep is in active development and used daily. The core implementations — memory, sessions, environment monitoring, coordination, replay, the client kit, and Symdex — are covered by more than 4,000 passing automated tests in the current repository. The architecture is designed for a single-host deployment.

This public, source-available repository is in early access.

License

Firekeep is source-available under BUSL-1.1, and self-hosted production use is free for individuals and for teams — a workspace of any size, on infrastructure you control, free for teams while Firekeep is in early access. The commercial tier is Enterprise governance and support (write to [email protected]). Each version converts to Apache-2.0 four years after its first public release. See LICENSE for the full grant and docs/LICENSING.md for status. Symdex remains under this license until its standalone Core is extracted and released separately under Apache-2.0.