Skip to content
Agentmart
Submit a tool

LLM Kosh

Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.

Connector by rastogivaibhav · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Chalk Labs

Need help deploying LLM Kosh?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/rastogivaibhav-llm-kosh

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
23 read · 7 write · 0 delete · 6 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 36

Read from the source code; the running server may list different tools.

Read 23 · Look things up without changing anything.

  • company_artifact_inspect
  • company_artifact_segment
  • company_artifact_snapshot
  • company_brain_health
  • company_episode_get
  • company_episodes_search
  • company_memory_get
  • company_memory_search
  • company_sessions_list
  • get_cartridge_memory_map
  • get_daemon_status
  • get_project_context
Show 11 more tools
  • intake_convert_file
  • kosh_verify
  • list_intake
  • reasoning_explore
  • reasoning_query
  • search_memory
  • trusted_memory_conflicts
  • trusted_memory_explain
  • trusted_memory_inbox
  • trusted_memory_recall
  • trusted_memory_review

Write 7 · Create, change, send or run things.

  • apply_intake_proposal
  • company_artifact_register
  • company_memory_propose
  • company_memory_propose_from_evidence
  • company_session_understand
  • create_private_context_pack
  • submit_memory_receipt

Not yet classified 6 · We could not tell from the name and description.

  • company_brain_evaluate
  • company_context_compile
  • company_memory_review
  • reasoning_critique
  • reasoning_ingest
  • trusted_memory_propose

Secrets and settings it asks for

Other settings (environment variables or headers).

  • CARTRIDGE_WORKSPACE

Files it touches

  • Any path the agent passes to its tools

Tools (36)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • apply_intake_proposal

    Directly applies an intake proposal batch to the live memory.

  • company_artifact_inspect

    Verify and inspect a bounded region of an authorized registered artifact.

  • company_artifact_register

    Register an existing local artifact by fingerprint without copying its bytes.

  • company_artifact_segment

    Inspect an artifact and persist bounded derived segments with native citations.

  • company_artifact_snapshot

    Explicitly materialize an authorized artifact into immutable snapshot storage.

  • company_brain_evaluate

    Run reference storage, citation, and projection acceptance checks.

  • company_brain_health

    Validate canonical company-brain storage and projection consistency.

  • company_context_compile

    Compile structured, cited, token-budgeted context for an agent task.

  • company_episode_get

    Get one authorized episode with ordered event and candidate provenance.

  • company_episodes_search

    Search authorized goal-oriented work episodes and observed outcomes.

  • company_memory_get

    Get one authorized memory with its evidence references and lifecycle.

  • company_memory_propose

    Create immutable evidence and a non-authoritative candidate memory.

  • company_memory_propose_from_evidence

    Create a candidate semantic memory citing an existing registered artifact.

  • company_memory_review

    Apply a governed lifecycle transition to an authorized memory.

  • company_memory_search

    Permission-first hybrid search over atomic, evidence-backed company memory.

Show 21 more tools
  • company_session_understand

    Build normalized sessions, episodes, and cited candidates from JSONL evidence.

  • company_sessions_list

    List authorized normalized source sessions.

  • create_private_context_pack

    Creates a highly focused context pack for a specific task. Includes private and sensitive information.

  • get_cartridge_memory_map

    Returns a structural map of the knowledge base projects and active concepts.

  • get_daemon_status

    Verifies the cryptographic ledger of the Cartridge.

  • get_project_context

    Fetches all context and active decisions for a specific project.

  • intake_convert_file

    Converts a local file (e.g. PDF, DOCX, XLSX, PPTX, PNG, WAV) to structured markdown using the MarkItDown converter and ingests it into the cartridge.

  • kosh_verify

    Verify a question against local temporal/causal evidence. This is read-only. The returned JSON report can include supporting facts, causal paths, contradictions, inferred-but-not-discovered relationships, missing evidence, stability information, and an explicit abstention state. It does not consult the internet, seed demo data, write or mutate memory, export private context, or make an imported source trustworthy.

  • list_intake

    Lists the current items pending in the intake queue.

  • reasoning_critique

    Run the Lyapunov critic on a specific list of fact IDs. Returns stability score, status, and per-dimension breakdown.

  • reasoning_explore

    Enumerate all causal paths between two known facts. Returns the fiber bundle for that specific pair.

  • reasoning_ingest

    Add a bounded atomic fact to the Temporal Causal Reasoning Graph. This is a write operation and requires --allow-write. documented_at and valid_from are ISO 8601 datetime strings. causal_edges: JSON array of {"target_id": str, "edge_type": str, "confidence": float}. Returns the new fact_id.

  • reasoning_query

    Query the Temporal Causal Reasoning Graph. By default returns a human-readable causal narrative (narrative=True). Set narrative=False to get raw JSON with full fiber bundle details. temporal_context: ISO 8601 datetime or Unix timestamp string (omit for now).

  • search_memory

    Search the Cartridge Knowledge Base for memories, decisions, and files.

  • submit_memory_receipt

    Submits a MEMORY_RECEIPT.md formatted string to the intake queue. Does not apply it directly; it must be reviewed and applied.

  • trusted_memory_conflicts

    List unresolved authorized Trusted Memory conflicts.

  • trusted_memory_explain

    Explain one authorized memory with evidence and admission history.

  • trusted_memory_inbox

    List authorized candidate and quarantined Trusted Memory items.

  • trusted_memory_propose

    Propose governed memory. Requires MCP write capability. If ``evidence_id`` is omitted, the proposal is persisted as an ``agent_observation``. Agents cannot self-label new MCP evidence as ``user_direct``. To preserve a stronger or different source type, register evidence first and pass its existing id.

  • trusted_memory_recall

    Recall governed memory with admission and lifecycle policy enforced.

  • trusted_memory_review

    Explicitly approve, quarantine, reject, or supersede governed memory. Requires the existing MCP mutate capability. Conflict resolution is never inferred from a generic approval.

Signals

Stars
1
Forks
1
Open issues
0
Weekly downloads
70
Last commit
Sep 14, 2026 (1 month ago)
Last release
Jun 23, 2026 (4 months ago)
Last package publish
Jun 23, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.rastogivaibhav/llm-kosh
Version
2.1.3
Auth
No auth
Packages
pypi llm-kosh
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get LLM Kosh running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying LLM Kosh?

CallGet help
Cite this page

LLM Kosh MCP server. Agent Mart. https://agentmart.dev/connectors/rastogivaibhav-llm-kosh (last updated 2026-10-24)