theGian7

Persistent memory + governance for AI coding agents.

Hybrid search, verbatim recall, knowledge graph, and passive capture for Claude Code — source-available, local-first, and shipping today. Works on Mac, Linux, and cloud. No hardware binding.

pip install team-intel-mcp
14 MCP Tools
Hybrid Search
Knowledge Graph
634 Tests Passing

Why AI coding agents forget.

Every team using Claude, Cursor, or Copilot has hit these four walls. team-intel answers each one with shipped code.

01 — Silent context death

Context compression hits mid-session.

“The model silently loses critical decisions made earlier in the conversation, then keeps generating with full confidence.”

Answer: hybrid search + verbatim recall. Every message is indexed in parallel with distilled extraction. When the top RRF score drops below the calibrated threshold, the RAG pipeline transparently falls back to raw message search. You search what was actually said, not just what was distilled.

02 — The cheerful yes-man

Frontier models agree with you 100% of the time.

“Even when you're wrong. Even when you contradicted yourself yesterday. The model has no memory of either.”

Answer: heuristic + gotcha artifacts retrieved by the same RAG pipeline. Saved insights push back with the user's prior corrections, not generic advice. A built-in reconciliation skill audits Claude memories against the knowledge base for drift.

03 — Anterograde amnesia

Every session is a blank slate.

“Frontier models cannot form long-term memories. Every new session, your team's hard-won context resets to zero.”

Answer: a passive capture hook records every tool use in under 10ms. A stop hook runs the extraction pipeline async, with a circuit breaker after three LLM failures. Knowledge survives across sessions, repositories, and machines.

04 — Zero governance

No enforced standards, no security scanning, no rules.

“The agent will happily merge insecure code, ignore your style guide, and forget last week's architectural decisions.”

Answer: shipped skills. /team-intel-backfill extracts institutional knowledge from git history. /refresh-claude-md audits CLAUDE.md against the actual code. /goodnight is an end-of-day sweep for uncommitted work and stale knowledge. Enforcement lives in skills and hooks, not LLM “please follow these rules” prose.

Three steps. Zero friction.

Knowledge capture that stays out of your way.

01
>_

Work Normally

Write code, debug, review PRs. Team Intel's capture hook runs in the background — less than 10ms overhead per tool call.

< 10ms overhead
02

Automatic Extraction

When your session ends, an LLM extracts structured knowledge: decisions you made, heuristics you discovered, playbooks you followed.

03

Instant Retrieval

Hybrid search (semantic + keyword + Reciprocal Rank Fusion) surfaces the right knowledge when you need it. Fresh results, not stale docs.

13 MCP Tools. Zero Overhead.

A complete knowledge management toolkit that integrates directly into your coding workflow.

team-intel — MCP tools
search_knowledgeHybrid semantic + keyword search
save_insightCapture decisions, heuristics, playbooks
ask_knowledgeNatural language Q&A with citations
get_contextRelevant knowledge for current file
link_knowledgeMap relationships between artifacts
browse_by_projectDiscover knowledge by project
digest_filesIngest markdown docs into the graph
...and 6 more

Hybrid Search

Semantic embeddings + BM25 keyword search fused with Reciprocal Rank Fusion. Get the best of both worlds — meaning and precision.

Knowledge Graph

NetworkX-powered graph maps relationships between decisions, people, and projects. Discover connections you didn't know existed.

Freshness Scoring

Artifacts decay over time, boosted by access patterns. Results are always relevant, never stale. The knowledge base curates itself.

LLM-Agnostic

Works with Ollama (free, local), Claude API, or deferred extraction. Your choice of model, your data stays where you want it.

Explore a Knowledge Graph

This is a real knowledge graph generated from development sessions. Drag nodes, explore connections.

Decisions
Heuristics
Playbooks
Checklists

Stop losing what your team knows.

Knowledge should outlive Slack threads and quit notices.

Bus Factor

Know who knows what. Identify expertise gaps before they become crises. Every decision is linked to its author and context.

Onboarding

New team members search the knowledge base instead of interrupting seniors. Ramp-up time drops from weeks to days.

Institutional Memory

Decisions outlive the people who made them. Context is never lost. "Why did we choose Postgres?" is always one search away.

Pitched vs shipped.

The AI-coding memory space has plenty of polished marketing. Here's what team-intel actually does, side by side with what the typical alternative does today.

Dimension Typical alternative team-intel
Install today Download links 404 after payment, TPM 2.0 required, Mac unsupported pip install team-intel-mcp — Mac, Linux, cloud, no hardware binding
Source availability Closed source with ambiguous IP lineage Source-available under Elastic License 2.0. Read, modify, and use it for yourself or your team
Test coverage Zero public tests 634 passing tests across core + MCP
Persistence In-memory dictionaries that vanish on restart SQLite + ChromaDB (individual) or Postgres with tenant isolation (team)
Knowledge graph Claimed in marketing copy Real. SQLite with temporal edges, entity registry, person aliases, merge primitives
Hybrid search Claimed “multi-channel RAG” Real. Semantic (Qwen3-Embedding-8B) + BM25 fused with Reciprocal Rank Fusion (k=60)
Verbatim recall Not offered Every session message indexed in parallel with extraction. Calibrated RRF fallback when distilled artifacts miss
LLM flexibility Anthropic-only Ollama + Claude API + deferred. Auto-detects backend at startup
Pricing $1,000–$5,000 per single user per month $0 forever for individuals. Team and enterprise tiers when you scale

Simple, transparent pricing.

Start free. Upgrade when your team grows.

Free
$0
individual, forever
Local MCP server. Read your own code. No limits, no expiration, no telemetry.
  • 14 MCP tools
  • Hybrid search + verbatim recall
  • Local SQLite + ChromaDB
  • Ollama or Claude API
  • Source-available (ELv2)
Install Now →
Pro
$19
per user / month
Cloud-managed extraction and cross-machine sync. Still single-user.
  • Everything in Free
  • Cloud-hosted extraction LLM
  • Cross-machine sync
  • Encrypted backup
  • Email support
Enterprise
$99
per user / month · or custom
25+ developers, regulated industries, on-prem available.
  • Everything in Team
  • SSO (SAML / OIDC)
  • Audit trail
  • On-prem option
  • SOC2 + contractual SLAs
  • Dedicated support
Contact Sales

Pro and Team tiers are landing soon.

The Free MCP server installs today. Get notified the moment cloud-managed extraction (Pro) and the multi-tenant team graph (Team) go GA.

No spam. Beta invitations and launch updates only.